© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 6760
    Prev
    Next
    INDEX
    Explanations

    instances of control flow statements, particularly "switch" cases in programming code

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

    programming constructs related to conditional 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
    rophes
    -0.52
    aarrggbb
    -0.52
     propellant
    -0.49
     etc
    -0.49
    oprot
    -0.49
    issory
    -0.49
     Nutt
    -0.48
    ioutil
    -0.48
     Programmer
    -0.48
     trilha
    -0.48
    POSITIVE LOGITS
    switch
    1.71
    Switch
    1.01
     switch
    0.96
     Switch
    0.95
     switches
    0.84
    }")]
    0.82
     switching
    0.77
     switched
    0.76
    SWITCH
    0.75
     SWITCH
    0.75
    Activations Density 0.026%

    No Known Activations