© 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. 11455
    Prev
    Next
    INDEX
    Explanations

    terms related to processes and actions impacting stability or effectiveness

    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
     comprando
    -0.59
    氓
    -0.58
     worshipped
    -0.56
     iscri
    -0.52
     flattered
    -0.51
     retired
    -0.51
     memu
    -0.51
    SUBSCRIBE
    -0.50
     geren
    -0.50
    を食べ
    -0.50
    POSITIVE LOGITS
    QMetaType
    0.76
     successful
    0.75
     brief
    0.74
    การ
    0.74
    المناصب
    0.73
    ệc
    0.73
     simultaneous
    0.72
    successful
    0.72
     erfolgt
    0.71
     yapılan
    0.70
    Activations Density 1.443%

    No Known Activations