© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3431
    Prev
    Next
    INDEX
    Explanations

    terms related to quantitative analysis and statistical data

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

    proper nouns and names, particularly surnames and geographic locations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    jší
    -0.45
    存于互联网档案馆
    -0.44
     canad
    -0.43
    니다
    -0.41
    сть
    -0.40
    ل
    -0.40
    TRAIT
    -0.40
    感じで
    -0.39
    습니다
    -0.38
    которые
    -0.37
    POSITIVE LOGITS
    ed
    1.33
    ized
    0.98
    ted
    0.77
    istered
    0.70
    ated
    0.67
    stood
    0.65
    ched
    0.63
    anteed
    0.62
    ened
    0.62
    tered
    0.62
    Activations Density 2.044%

    No Known Activations