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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 8762
    Prev
    Next
    INDEX
    Explanations

    patterns related to operations and commands in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -1.29
    </u>
    -1.02
    </i>
    -1.00
    </h5>
    -0.99
     */
    -0.75
    ."—
    -0.63
     [
    -0.61
     ‚
    -0.60
    .”
    -0.59
    ”
    -0.59
    POSITIVE LOGITS
    expandindo
    1.05
     tartalomajánló
    1.04
    tagHelperRunner
    1.02
    WireFormatLite
    0.97
    mybatisplus
    0.91
     CreateTagHelper
    0.87
    =$?
    0.73
     виправивши
    0.72
     protoimpl
    0.72
    ']")
    0.71
    Activations Density 0.730%

    No Known Activations