© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8808
    Prev
    Next
    INDEX
    Explanations

    elements related to data processing and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical and scientific concepts described through formal academic or technical language.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.57
    routeProvider
    -0.50
     Bung
    -0.49
    Toponymie
    -0.48
    featureID
    -0.47
     dortmund
    -0.46
    URLException
    -0.46
     AspNetCore
    -0.46
     Matters
    -0.44
    HostException
    -0.44
    POSITIVE LOGITS
     asupra
    1.19
     върху
    1.15
     upon
    1.02
     applied
    0.99
     onto
    0.91
    applied
    0.83
    upon
    0.79
     vpon
    0.77
     terhadap
    0.73
     sobre
    0.73
    Activations Density 0.952%

    No Known Activations