© 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. 7-GEMMASCOPE-RES-16K
    6. 11909
    Prev
    Next
    INDEX
    Explanations

    instances of programming control flow structures, particularly switch statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Extent
    -0.53
     engagé
    -0.53
     fact
    -0.53
    يفة
    -0.51
     vett
    -0.49
     препратки
    -0.49
     consciência
    -0.48
    Plane
    -0.48
     már
    -0.48
     extent
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.88
    ParallelGroup
    0.87
    ILayout
    0.87
    ResumeLayout
    0.83
     nahilalakip
    0.83
    Datuak
    0.80
     كومونز
    0.79
    matchCondition
    0.78
     AspNetCore
    0.78
    IBOutlet
    0.78
    Activations Density 0.029%

    No Known Activations