© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14586
    Prev
    Next
    INDEX
    Explanations

    expressions of changed or repeated actions

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

    phrases indicating repeated actions or multiple occurrences of something.

    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
    IntoConstraints
    -0.57
    TagMode
    -0.42
    èdia
    -0.42
    tvguidetime
    -0.40
    annica
    -0.36
     Référence
    -0.36
    новниш
    -0.35
     ویکی‌پدیا
    -0.35
    ArgsConstructor
    -0.35
    كويكب
    -0.35
    POSITIVE LOGITS
     repeatedly
    2.53
     twice
    2.42
    twice
    2.14
     mehrm
    2.13
     thrice
    2.00
     mehrfach
    2.00
     Twice
    1.99
    多次
    1.98
    Twice
    1.95
     multiple
    1.95
    Activations Density 1.360%

    No Known Activations