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
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 383
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, specifically for defining classes, methods, and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seguida
    -0.43
    kömm
    -0.42
    like
    -0.41
    kjø
    -0.41
    räck
    -0.41
    and
    -0.41
    A
    -0.39
    -
    -0.39
    windowFixed
    -0.39
    K
    -0.38
    POSITIVE LOGITS
    URLException
    0.71
     ویکی‌پدیای
    0.65
    ⦑
    0.65
    帖最后由
    0.63
    にほんブログ村
    0.63
     noDo
    0.62
     ""],
    0.62
    )_/¯
    0.61
     ๆ
    0.60
    ſehen
    0.59
    Activations Density 2.570%

    No Known Activations