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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5364
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software and file systems

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

    technical specifications and performance metrics in specialized systems and protocols.

    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
     مرئيه
    -0.62
    ScopeManager
    -0.59
    UserScript
    -0.59
     Numerade
    -0.48
    ThroughAttribute
    -0.47
    évaluateur
    -0.47
    EndGlobalSection
    -0.46
    */].
    -0.45
    EndProject
    -0.45
    Consig
    -0.44
    POSITIVE LOGITS
     redundancy
    1.64
     redundant
    1.46
     Redund
    1.34
    redund
    1.30
     redund
    1.30
    Redund
    1.27
     reliability
    1.03
    冗
    1.01
     Reliability
    0.87
     fault
    0.85
    Activations Density 0.562%

    No Known Activations