© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13891
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations related to solving equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     défend
    -0.40
    äfts
    -0.37
     pungkas
    -0.36
    ñora
    -0.35
    antaranya
    -0.34
     contactez
    -0.33
     ucapnya
    -0.33
    lijck
    -0.32
    execSQL
    -0.31
    onOptions
    -0.31
    POSITIVE LOGITS
     MainAxisSize
    0.69
    AsUp
    0.63
    findpost
    0.61
    NameInMap
    0.57
     knowing
    0.56
     missing
    0.56
    oredCriteria
    0.55
     jspb
    0.53
    quisa
    0.52
     propOrder
    0.50
    Activations Density 1.059%

    No Known Activations