© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 7562
    Prev
    Next
    INDEX
    Explanations

    expressions related to obscured or unintelligible content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     """
    -0.69
    posób
    -0.68
     confronti
    -0.68
    IBarButtonItem
    -0.66
     BorderSide
    -0.65
    triangleq
    -0.64
    astify
    -0.64
    )");
    -0.64
     SqlDbType
    -0.61
    /**
    -0.60
    POSITIVE LOGITS
    ########.
    0.56
     mumbled
    0.54
     muttered
    0.54
     snat
    0.50
    TagHelpers
    0.50
    intelligible
    0.47
     vaguely
    0.45
    朦
    0.45
    nible
    0.43
    èvement
    0.42
    Activations Density 0.348%

    No Known Activations