© 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. 20-GEMMASCOPE-RES-16K
    6. 11873
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and classes, particularly those associated with file handling and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of programming library or framework identifiers, especially utility/helper classes and modules within code snippets.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     besseren
    -0.43
     kleineren
    -0.42
    UIControlState
    -0.41
     gastar
    -0.40
     hohem
    -0.40
    ?}",
    -0.39
    คนที่
    -0.39
    ยาว
    -0.39
     desafíos
    -0.39
     creciente
    -0.39
    POSITIVE LOGITS
    protoimpl
    0.79
    VIAF
    0.66
     مشين
    0.63
     SafeMath
    0.63
     MainAxisSize
    0.60
    arangay
    0.60
     kaarangay
    0.59
    Autoritní
    0.59
    ualaikum
    0.59
    WireFormatLite
    0.58
    Activations Density 0.182%

    No Known Activations