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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21837
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific identifiers related to scientific methods or data

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

    ijerph-17

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Chwiliwch
    -1.03
    MigrationBuilder
    -1.02
     CreateTagHelper
    -0.96
     NSCoder
    -0.92
    QMetaType
    -0.91
    protoimpl
    -0.89
     ProtoMessage
    -0.88
    iſchen
    -0.88
    ロウィン
    -0.86
    niſſe
    -0.85
    POSITIVE LOGITS
    </b>
    0.43
    </strong>
    0.42
    </h2>
    0.36
     apud
    0.32
    Env
    0.31
     per
    0.31
    </h3>
    0.30
    </h1>
    0.30
    AD
    0.29
    …
    0.28
    Activations Density 0.002%

    No Known Activations