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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14644
    Prev
    Next
    INDEX
    Explanations

    database operations and commands related to search functionality

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

    Code tokens followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    code syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.01
    RegressionTest
    -0.67
    (!__
    -0.65
    Rüyada
    -0.65
    sizeCache
    -0.60
    []=$
    -0.59
     &___
    -0.58
    écial
    -0.58
     human
    -0.57
    üyada
    -0.57
    POSITIVE LOGITS
     Shakspeare
    0.63
     Cæsar
    0.62
     calendriers
    0.60
     hentai
    0.58
     geldig
    0.58
     الحره
    0.54
    brainly
    0.53
    QUADS
    0.53
     alimentaires
    0.53
     buddha
    0.53
    Activations Density 0.212%

    No Known Activations