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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7882
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer, particularly malignant transformation and tumor growth factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    TargetException
    -0.67
    AnimationsModule
    -0.67
    Obrázky
    -0.65
    msgTypes
    -0.64
    makeConstraints
    -0.63
     חיצוניים
    -0.61
    IBarButtonItem
    -0.60
    ActionCreators
    -0.59
    RunWith
    -0.58
    IntoConstraints
    -0.58
    POSITIVE LOGITS
    UnusedPrivate
    0.61
    ografija
    0.51
    endmodule
    0.44
     Itself
    0.43
    misen
    0.42
    mord
    0.42
    evento
    0.42
    >[]
    0.41
     itself
    0.41
    +][
    0.41
    Activations Density 2.406%

    No Known Activations