© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 12359
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and methods related to event handling and object manipulation

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

    target following expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isamment
    -0.31
     acestei
    -0.31
     protoimpl
    -0.30
    luß
    -0.30
     MonoBehaviour
    -0.28
     piedi
    -0.28
     dipendenti
    -0.28
     dumne
    -0.27
    illos
    -0.26
     crochê
    -0.26
    POSITIVE LOGITS
     target
    1.11
    target
    1.02
     TARGET
    0.91
    TARGET
    0.86
    TargetException
    0.85
     targets
    0.82
    arget
    0.79
    Target
    0.79
     taget
    0.78
     Target
    0.77
    Activations Density 0.014%

    No Known Activations