Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114941
    Prev
    Next
    INDEX
    Explanations

    expressions of personal annoyance and emotional disturbances

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

    Personal pronouns (especially "me") that appear in contexts where someone expresses being emotionally affected, bothered, confused, or disturbed by something.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    帖最后由
    -0.65
     للاسماء
    -0.59
    AddTagHelper
    -0.51
    Gemeinden
    -0.51
    präch
    -0.49
    MessageTagHelper
    -0.46
     собі
    -0.45
     watchdog
    -0.45
     ویکی‌پدیا
    -0.44
     poveznice
    -0.44
    POSITIVE LOGITS
     profundamente
    0.40
    Leif
    0.38
    est
    0.37
    Deep
    0.37
    august
    0.36
    ッセイ
    0.36
    inspire
    0.35
    isEmpty
    0.35
    seem
    0.34
     känns
    0.34
    Activations Density 0.026%

    No Known Activations