© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 6967
    Prev
    Next
    INDEX
    Explanations

    statements or questions related to conditional logic or assertions concerning scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    standardized multiple-choice question text, including prompts, answer-choice structures, and selection instructions.

    oai_token-act-pair · gpt-5Triggered by @areeb0102

    multiple-choice question structures.

    oai_token-act-pair · deepseek-r1Triggered by @areeb0102

    multiple-choice question structures and their characteristic phrasing patterns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Espèce
    -0.68
    endpush
    -0.67
    MLLoader
    -0.65
     Magdalen
    -0.60
     متعلقه
    -0.59
     utafiti
    -0.59
    WriteTagHelper
    -0.59
    TypedDataSet
    -0.58
     installments
    -0.58
    KommentareTeilen
    -0.57
    POSITIVE LOGITS
     correct
    0.68
     CORRECT
    0.62
     corret
    0.61
     Correct
    0.60
     correctly
    0.59
     corect
    0.58
     Bomb
    0.51
    correct
    0.50
     通販
    0.50
     Radio
    0.50
    Activations Density 0.930%

    No Known Activations