© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1441
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data manipulation and session management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
     betweenstory
    -0.61
     snippetHide
    -0.49
     astore
    -0.49
    cember
    -0.49
     Cataloging
    -0.49
     gynhyrchwyd
    -0.49
    nezeu
    -0.47
    parsedMessage
    -0.46
    scribers
    -0.45
    󠁴
    -0.45
    POSITIVE LOGITS
    zzleHttp
    0.49
    stateMutability
    0.37
     geslacht
    0.36
    Vaata
    0.35
    setdefault
    0.35
    kreuz
    0.35
    RetentionPolicy
    0.34
     frattempo
    0.34
     createSlice
    0.33
    chein
    0.33
    Activations Density 0.200%

    No Known Activations