© 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. 34-GEMMASCOPE-RES-16K
    6. 11364
    Prev
    Next
    INDEX
    Explanations

    specific quantitative descriptors and assertions regarding groups or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exceptions
    -0.69
     loopholes
    -0.66
     mogelijkheden
    -0.66
     caveats
    -0.65
     hearings
    -0.65
     muscles
    -0.65
     outliers
    -0.65
     capacitors
    -0.64
     priorities
    -0.64
     anomalies
    -0.63
    POSITIVE LOGITS
     stuff
    1.01
     legislation
    0.96
     enfans
    0.83
     Stuff
    0.83
    stuff
    0.83
     footage
    0.82
    Stuff
    0.82
     circuitry
    0.79
    legislation
    0.79
     imagery
    0.76
    Activations Density 1.168%

    No Known Activations