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. 1833
    Prev
    Next
    INDEX
    Explanations

    punctuation related to string operations and file paths

    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
     
    -0.60
    <em>
    -0.58
    <u>
    -0.56
    le
    -0.53
    <i>
    -0.52
    ta
    -0.49
    läg
    -0.49
    Le
    -0.49
    卑
    -0.48
    est
    -0.48
    POSITIVE LOGITS
    MessageTagHelper
    0.88
    TintMode
    0.82
    󠁴
    0.80
    ViewFeatures
    0.78
    parsedMessage
    0.78
    ///</
    0.78
    SharedCtor
    0.78
     >=",
    0.76
    AccessorTable
    0.76
    protoimpl
    0.76
    Activations Density 0.426%

    No Known Activations