Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8028
    Prev
    Next
    INDEX
    Explanations

    conditional statements, particularly those starting with "if"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.65
    GenerationType
    -0.65
     GreatSchools
    -0.63
    didSet
    -0.62
    inguish
    -0.61
    migrationBuilder
    -0.59
    ouncements
    -0.57
    LLocation
    -0.57
    conio
    -0.57
    oporosis
    -0.56
    POSITIVE LOGITS
    If
    0.66
    jalá
    0.64
    featureID
    0.60
     dacă
    0.59
     اگه
    0.58
     hvis
    0.55
     If
    0.55
    אם
    0.54
     if
    0.54
     gynhyrchwyd
    0.53
    Activations Density 0.182%

    No Known Activations