© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10504
    Prev
    Next
    INDEX
    Explanations

    intense emotional expressions and complex social themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before "to" or punctuation

    np_acts-logits-general · gemini-2.0-flash

    concrete descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.91
    DockStyle
    -0.79
    bootstrapcdn
    -0.78
     Савезне
    -0.76
    
    -0.71
    
    -0.71
    <unused52>
    -0.68
     パンチラ
    -0.68
    <unused0>
    -0.68
    <unused23>
    -0.68
    POSITIVE LOGITS
     hver
    0.28
     novedad
    0.26
     acá
    0.26
    Fuß
    0.26
    leitung
    0.25
     good
    0.25
    WebMethod
    0.24
    gefahr
    0.23
    var
    0.23
    Far
    0.23
    Activations Density 1.134%

    No Known Activations