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. 0-GEMMASCOPE-RES-16K
    6. 9700
    Prev
    Next
    INDEX
    Explanations

    references to a specific academic or scientific topic related to "Schizophrenia."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Warm
    -0.52
    الحياه
    -0.50
    textStyle
    -0.45
     reserve
    -0.45
     warm
    -0.45
     posse
    -0.45
     Flat
    -0.44
     fancy
    -0.44
     Special
    -0.44
     sense
    -0.42
    POSITIVE LOGITS
    jsonwebtoken
    0.58
     législation
    0.54
     AssemblyCulture
    0.54
    ContentLoaded
    0.53
     Krankheiten
    0.53
    Général
    0.52
    aarrggbb
    0.52
     lancement
    0.52
     afbeeldingen
    0.51
     nación
    0.51
    Activations Density 0.281%

    No Known Activations