© 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. 13-GEMMASCOPE-RES-16K
    6. 8686
    Prev
    Next
    INDEX
    Explanations

    awards and achievements in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.65
    AxisAlignment
    -0.64
    ècie
    -0.63
    Parcelize
    -0.62
    routeProvider
    -0.61
    ambiguation
    -0.61
    expandindo
    -0.60
    Clik
    -0.60
    SBATCH
    -0.59
     []:
    -0.59
    POSITIVE LOGITS
     lifetime
    0.59
    Lifetime
    0.56
     Lifetime
    0.52
     ecos
    0.49
    Heartbeat
    0.49
     twofold
    0.49
     eyewitness
    0.48
     marketplace
    0.47
     nationwide
    0.46
     healthcare
    0.46
    Activations Density 1.159%

    No Known Activations