© 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. 41-GEMMASCOPE-RES-16K
    11. 6809
    Prev
    Next
    INDEX
    Explanations

    various technical terms and methodologies related to software and algorithmic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    četně
    -0.42
    enderror
    -0.40
     sposa
    -0.38
     BoxFit
    -0.38
    Personendaten
    -0.36
    Results
    -0.35
    InitVars
    -0.35
     primas
    -0.34
    তথ্যসূত্র
    -0.34
    uxxxx
    -0.33
    POSITIVE LOGITS
     analyzes
    0.98
     studies
    0.96
     tracks
    0.93
     examines
    0.89
     analyses
    0.87
     checks
    0.84
     reviews
    0.83
     looks
    0.81
     evaluates
    0.77
     measures
    0.76
    Activations Density 0.523%

    No Known Activations