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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 399
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with statistics in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    
    -0.65
    Diwedd
    -0.61
    …"
    -0.57
    '>";
    -0.56
     autorytatywna
    -0.55
    "
    -0.53
     <",
    -0.53
    </b>
    -0.52
    adag
    -0.51
    </u>
    -0.51
    POSITIVE LOGITS
    DockStyle
    0.87
    ilibrium
    0.75
     fertiliser
    0.72
    EFIAPI
    0.72
     BigDecimal
    0.72
    EReference
    0.71
    RetentionPolicy
    0.71
    GLint
    0.70
    synthesize
    0.70
    GtkWidget
    0.69
    Activations Density 0.001%

    No Known Activations