© 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. 12803
    Prev
    Next
    INDEX
    Explanations

    instances of things being filled or loaded

    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
     ModelExpression
    -0.60
     HttpNotFound
    -0.56
    toThrow
    -0.55
    garek
    -0.54
     ApiException
    -0.53
    $_['
    -0.50
    FieldBuilder
    -0.48
     ſtate
    -0.48
    .*")]
    -0.47
     useParams
    -0.47
    POSITIVE LOGITS
     filled
    2.05
     populated
    2.02
     Filled
    1.83
    filled
    1.72
    Filled
    1.71
     loaded
    1.65
     packed
    1.63
    populated
    1.52
     inhabited
    1.51
     Packed
    1.41
    Activations Density 0.206%

    No Known Activations