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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3338
    Prev
    Next
    INDEX
    Explanations

    architectural details and descriptions of buildings

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

    followed by a date or version

    np_acts-logits-general · gemini-2.0-flash

    numbers, descriptive features, or styles

    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
     كومونز
    -0.63
    nodoc
    -0.63
     Conſ
    -0.61
    évaluateur
    -0.61
     defaultstate
    -0.60
     насељу
    -0.60
    ########.
    -0.59
     مشين
    -0.58
     Савезне
    -0.54
     Anſ
    -0.54
    POSITIVE LOGITS
     crossorigin
    0.29
    Sprache
    0.29
     hospital
    0.28
     port
    0.28
     starters
    0.28
    "}";
    0.27
    toggler
    0.27
     Reeves
    0.27
     konuş
    0.26
    TargetException
    0.26
    Activations Density 0.198%

    No Known Activations