Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 3633
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags and their attributes in web documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parcelize
    -0.61
    RefNanny
    -0.57
     CURIAM
    -0.56
     Personality
    -0.53
    featureID
    -0.52
    SharedDtor
    -0.52
    personality
    -0.51
    ьаж
    -0.51
    SourceChecksum
    -0.51
    parsedMessage
    -0.49
    POSITIVE LOGITS
     http
    2.69
    http
    2.53
    Http
    1.85
     Http
    1.81
     HTTP
    1.72
     https
    1.59
    HTTP
    1.53
    https
    1.42
     htt
    1.29
    ttp
    1.24
    Activations Density 0.450%

    No Known Activations