© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 16253
    Prev
    Next
    INDEX
    Explanations

    phrases expressing skepticism or doubt about claims or situations

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

    explicit negation, especially “not” and negative contractions indicating denial, inability, or refusal.

    oai_token-act-pair · gpt-5Triggered by @areeb0102

    expressions of negation.

    oai_token-act-pair · deepseek-r1Triggered by @areeb0102

    negation and denial expressions, particularly contractions with "not" or negative statements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сього
    -0.58
     quoque
    -0.57
     gerichtet
    -0.55
    先是
    -0.55
     sometime
    -0.53
    eventually
    -0.52
     vervolgens
    -0.51
    dirig
    -0.51
     eventualmente
    -0.50
    uparrow
    -0.50
    POSITIVE LOGITS
    RTDA
    0.91
     any
    0.85
     necessarily
    0.84
     nor
    0.81
     ningún
    0.79
    تقاوى
    0.79
    hoeddwyd
    0.78
     siquiera
    0.78
    ArrowToggle
    0.77
     unless
    0.77
    Activations Density 1.003%

    No Known Activations