© 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
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3095
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rejected" and related terms in the context of decisions or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.82
    存于互联网档案馆
    -0.62
    EDEFAULT
    -0.59
    TintMode
    -0.56
     ब्रेकडाउन
    -0.56
     OMIT
    -0.55
    новниш
    -0.53
    ьаж
    -0.51
     Wikimedijinoj
    -0.51
     صوتيه
    -0.51
    POSITIVE LOGITS
    en
    0.64
    lehre
    0.46
     Online
    0.45
    online
    0.45
    Online
    0.43
     please
    0.43
     never
    0.40
    bach
    0.40
     Bore
    0.40
    mbolo
    0.39
    Activations Density 0.200%

    No Known Activations