© 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. 31-GEMMASCOPE-RES-16K
    6. 3563
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to coding or software development

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

    code and technical documentation with special emphasis on API specifications, package declarations, and licensing headers.

    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
     Bewußt
    -0.52
     demografica
    -0.36
    insics
    -0.35
     gyermek
    -0.34
    argli
    -0.34
     eksp
    -0.34
     Soccerway
    -0.33
    生
    -0.33
    enderror
    -0.32
    oredCriteria
    -0.32
    POSITIVE LOGITS
     Pod
    0.57
    IntoConstraints
    0.56
     Pods
    0.56
     pod
    0.55
    はじめに
    0.54
    Pod
    0.53
     mergeFrom
    0.52
    MarshalTo
    0.52
     Kubernetes
    0.50
     pods
    0.49
    Activations Density 0.249%

    No Known Activations