© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 1432
    Prev
    Next
    INDEX
    Explanations

    phrases involving control and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.72
    دانشنامهٔ
    -0.69
    WebVitals
    -0.68
    expandindo
    -0.66
     hinaus
    -0.60
    jsxFileName
    -0.59
    contentLoaded
    -0.56
     propOrder
    -0.56
    
    -0.55
    msgTypes
    -0.55
    POSITIVE LOGITS
     over
    4.13
    over
    3.07
    Over
    2.83
     Over
    2.81
     OVER
    2.73
     över
    2.52
    OVER
    2.27
     über
    2.19
    overs
    1.96
     над
    1.89
    Activations Density 2.179%

    No Known Activations