© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 4465
    Prev
    Next
    INDEX
    Explanations

    questions and answers related to numerical values, particularly in the context of comparisons and calculations

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

    multiple choice answer options in standardized tests, particularly identifying the answer choices labeled a, b, c, and d.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    multiple-choice answer options marked with letters in parentheses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.45
    latego
    -0.43
     AppCompatTheme
    -0.43
     vectoriales
    -0.43
     επίσης
    -0.43
    idän
    -0.43
     "..\..\..\
    -0.42
     Heizung
    -0.40
    Síguenos
    -0.40
     kohta
    -0.40
    POSITIVE LOGITS
    none
    0.56
     none
    0.50
     NSM
    0.47
    ambar
    0.47
    mS
    0.45
     يتيمه
    0.45
    None
    0.43
     None
    0.43
     Amb
    0.42
    IMS
    0.42
    Activations Density 0.263%

    No Known Activations