Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16329
    Prev
    Next
    INDEX
    Explanations

    spaces or tab characters used for formatting

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

    `tz.transition` followed by numerical values

    np_acts-logits-general · gemini-2.0-flash

    tz.transition, times, logs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    SequentialGroup
    -0.51
    iyle
    -0.51
     nahilalakip
    -0.48
    ckså
    -0.47
    VersionUID
    -0.46
    ására
    -0.45
    ñora
    -0.44
    不一樣
    -0.43
     wikipagina
    -0.43
    seamnă
    -0.43
    POSITIVE LOGITS
    <bos>
    1.13
     Italijanski
    0.49
    Shots
    0.49
    "]=
    0.48
    )』
    0.48
    blest
    0.47
     }}$}
    0.47
    ')}
    0.47
    shaft
    0.47
    }}}}
    0.46
    Activations Density 1.675%

    No Known Activations