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. 9-GEMMASCOPE-RES-16K
    6. 3793
    Prev
    Next
    INDEX
    Explanations

    references to the context of an object-oriented programming, specifically the use of 'this' and 'self' in a code environment

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

    "this" followed by specific punctuation

    np_acts-logits-general · gemini-2.0-flash

    javascript object access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.40
    <bos>
    -0.40
    ↵↵
    -0.34
     referenties
    -0.33
    stånd
    -0.32
     />;
    -0.31
     verkar
    -0.30
    jemahan
    -0.29
    ChrTalk
    -0.29
     hjelp
    -0.29
    POSITIVE LOGITS
    <unused8>
    0.73
    [@BOS@]
    0.73
    <unused43>
    0.72
    <unused55>
    0.72
    <unused21>
    0.72
    <unused16>
    0.72
    <unused28>
    0.72
    <unused41>
    0.72
    <unused1>
    0.72
    <unused3>
    0.72
    Activations Density 0.054%

    No Known Activations