© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15646
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular immune responses and the mechanisms of action involved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adamson
    -0.59
     Scotts
    -0.55
    /******/
    -0.54
     DBNull
    -0.54
    itrile
    -0.53
     Petron
    -0.53
    IntoConstraints
    -0.52
    før
    -0.51
     Stefani
    -0.51
     knex
    -0.49
    POSITIVE LOGITS
     immune
    1.29
     immunological
    1.09
     immun
    1.08
     immunity
    1.08
     Immune
    1.07
    Immune
    1.04
     Immunol
    1.03
    immune
    1.01
     Immun
    1.00
    immun
    0.97
    Activations Density 1.717%

    No Known Activations