© 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. 4-GEMMASCOPE-RES-16K
    11. 1784
    Prev
    Next
    INDEX
    Explanations

    instances of numeric values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.99
     ſtate
    -0.96
     deſt
    -0.93
     }}"></
    -0.92
     ſeveral
    -0.92
    GraphicsUnit
    -0.91
     ſche
    -0.90
     purpoſe
    -0.88
     Anſ
    -0.87
     ſever
    -0.85
    POSITIVE LOGITS
     years
    0.55
     (
    0.53
    føre
    0.53
     I
    0.52
     year
    0.52
    RIDE
    0.51
     az
    0.50
     
    0.50
     non
    0.50
    ual
    0.50
    Activations Density 0.308%

    No Known Activations