© 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. 2-GEMMASCOPE-RES-16K
    6. 8079
    Prev
    Next
    INDEX
    Explanations

    references to assemblies and audits in a technical or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.43
    Aktualisiert
    -0.40
     Kild
    -0.39
     decorazione
    -0.38
     Raquel
    -0.37
    ToProps
    -0.37
     Trigon
    -0.37
     Braxton
    -0.36
    RuleContext
    -0.36
     навча
    -0.36
    POSITIVE LOGITS
     weld
    0.84
     welds
    0.77
     welded
    0.70
     welding
    0.70
     glasses
    0.68
    weld
    0.68
     Weld
    0.66
     Glasses
    0.66
     audit
    0.63
    Weld
    0.63
    Activations Density 0.315%

    No Known Activations