© 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. 21-GEMMASCOPE-RES-16K
    6. 2679
    Prev
    Next
    INDEX
    Explanations

    references to teams and groups involved in various professional or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.56
    tonode
    -0.52
    mtrl
    -0.52
    StructEnd
    -0.51
    IonicModule
    -0.51
    GEBURTSDATUM
    -0.48
    uxxxx
    -0.48
    TagMode
    -0.48
    ppuden
    -0.47
     незавершена
    -0.47
    POSITIVE LOGITS
     officials
    0.56
     experts
    0.55
    Officials
    0.54
    Officers
    0.53
     investigators
    0.52
     Experten
    0.50
     officers
    0.50
     negotiators
    0.50
     technicians
    0.50
     bureaucrats
    0.49
    Activations Density 0.448%

    No Known Activations