© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12762
    Prev
    Next
    INDEX
    Explanations

    numerical data and values related to measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.48
    EDEFAULT
    -0.47
    awtextra
    -0.42
     comuniques
    -0.40
    DriverManager
    -0.40
    AsUp
    -0.39
    addComponent
    -0.39
    IGENCE
    -0.39
    Brainz
    -0.39
     [*]
    -0.39
    POSITIVE LOGITS
    出版年
    0.65
    expandindo
    0.61
    Życiorys
    0.59
     հղումներ
    0.46
     يتيمه
    0.46
    SharedCtor
    0.44
     Grüsse
    0.44
    aarrggbb
    0.41
    évaluateur
    0.41
     étoit
    0.40
    Activations Density 0.753%

    No Known Activations