© 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. 65292
    Prev
    Next
    INDEX
    Explanations

    expressions of negation or reluctance related to future actions or possibilities

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

    never followed by verb

    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
     siempre
    -0.55
     blijven
    -0.52
     sempre
    -0.49
    Always
    -0.49
     Always
    -0.47
    Siempre
    -0.46
    always
    -0.46
     always
    -0.45
     всегда
    -0.45
     selalu
    -0.45
    POSITIVE LOGITS
    parsedMessage
    0.60
     forget
    0.59
    featureID
    0.57
    存于互联网档案馆
    0.57
    MLLoader
    0.55
    httphttps
    0.54
    bnf
    0.54
     understand
    0.53
    extAlignment
    0.52
    roglo
    0.52
    Activations Density 0.017%

    No Known Activations