© 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. 11298
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate sequential or subsequent actions or events

    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
     Yag
    -0.81
     Eisenberg
    -0.75
     Veld
    -0.74
     McCarty
    -0.72
     Ramesh
    -0.71
     Haram
    -0.70
     Kos
    -0.70
     Pemberton
    -0.69
    oldValue
    -0.68
     חיצוניים
    -0.68
    POSITIVE LOGITS
    following
    1.87
     following
    1.83
    follow
    1.80
     follow
    1.79
     Following
    1.79
    Following
    1.76
     Follows
    1.73
    Follow
    1.65
     FOLLOW
    1.64
     follows
    1.63
    Activations Density 0.111%

    No Known Activations