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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 14808
    Prev
    Next
    INDEX
    Explanations

    achievements and awards in athletic careers

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

    Following a hyphen or number

    np_acts-logits-general · gemini-2.0-flash

    start of achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.41
     professionali
    -0.36
     cens
    -0.35
    uxxxx
    -0.33
     Normdatei
    -0.32
     censo
    -0.32
    муж
    -0.32
    httphttps
    -0.30
     anonyme
    -0.30
    neſs
    -0.30
    POSITIVE LOGITS
    érables
    0.51
     Außer
    0.48
    сылкі
    0.47
     graduating
    0.46
    <>(
    0.46
    "]]
    0.46
    Finishing
    0.46
    addPreferredGap
    0.45
     graduated
    0.45
    Descubre
    0.45
    Activations Density 0.187%

    No Known Activations