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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 45458
    Prev
    Next
    INDEX
    Explanations

    identifiers related to legal and scientific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    AndEndTag
    -1.17
     ModelExpression
    -1.13
     незавершена
    -1.09
    GOTREF
    -1.02
    OGND
    -0.94
    <unused28>
    -0.92
    [@BOS@]
    -0.92
    <unused8>
    -0.92
    <pad>
    -0.92
    <unused16>
    -0.92
    POSITIVE LOGITS
     neumáticos
    0.28
    <b>
    0.27
    <i>
    0.26
    #
    0.26
    <
    0.24
    <blockquote>
    0.24
     nyky
    0.23
    ↵↵
    0.23
    Tr
    0.23
     entier
    0.23
    Activations Density 0.161%

    No Known Activations