© 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. 15050
    Prev
    Next
    INDEX
    Explanations

    data types and their declarations

    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
     NSCoder
    -0.90
    tinyos
    -0.87
    ^(@)
    -0.82
     Lasso
    -0.82
     relever
    -0.82
     dépos
    -0.81
    ✨:
    -0.81
    ddots
    -0.79
    addCriterion
    -0.79
     Remedies
    -0.78
    POSITIVE LOGITS
     Int
    1.73
    Int
    1.63
     int
    1.36
     INT
    1.28
    int
    1.23
    INT
    1.19
     ints
    1.18
     getInt
    1.17
     INTR
    1.12
    Ints
    1.09
    Activations Density 0.118%

    No Known Activations