© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11304
    Prev
    Next
    INDEX
    Explanations

    statements punctuated by periods

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

    transitions or pivotal moments in personal narratives, often marked by temporal shifts and resumption of activities.

    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
     تضيفلها
    -0.65
     referrerpolicy
    -0.63
    цездатний
    -0.63
    ագրություններ
    -0.60
    bootstrapcdn
    -0.58
     BoxFit
    -0.57
    addComponent
    -0.56
    httphttps
    -0.54
    TargetException
    -0.53
    )_/¯
    -0.50
    POSITIVE LOGITS
     since
    1.62
     subsequent
    1.56
     subsequently
    1.53
     thereafter
    1.48
     depuis
    1.41
     Since
    1.39
    Since
    1.37
     Subsequent
    1.35
    since
    1.35
     sejak
    1.30
    Activations Density 0.474%

    No Known Activations