© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 11555
    Prev
    Next
    INDEX
    Explanations

    occurrences of conditional statements in code, specifically "else"

    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
     NgModule
    -0.62
    Referencies
    -0.60
     ISA
    -0.58
    cinnati
    -0.55
     Injectable
    -0.54
    contentPane
    -0.53
    anneau
    -0.53
    mpotent
    -0.52
    manship
    -0.52
     EventArgs
    -0.50
    POSITIVE LOGITS
     дописавши
    0.95
    Personensuche
    0.93
    Geplaatst
    0.93
    principalTable
    0.84
     ModelExpression
    0.84
    else
    0.79
    uxxxx
    0.77
    enumii
    0.75
     PyLong
    0.73
    __':
    0.72
    Activations Density 0.031%

    No Known Activations