© 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. 7498
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions or feelings about fairness and practicality

    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
     sof
    -0.53
     net
    -0.52
     Loeb
    -0.51
     reg
    -0.51
    ον
    -0.50
     Mag
    -0.49
     Ver
    -0.49
     “
    -0.49
     Due
    -0.48
     ‘
    -0.48
    POSITIVE LOGITS
    PerformLayout
    0.92
    UnsafeEnabled
    0.79
    seemed
    0.78
    featureID
    0.76
     initComponents
    0.76
    StoreMessageInfo
    0.74
    脚注の使い方
    0.74
     seemed
    0.73
     zelve
    0.71
     sounded
    0.70
    Activations Density 0.133%

    No Known Activations