© 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. 4445
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in text

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

    end-of-sentence punctuation followed by content summaries or transitions to new sections.

    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
     كومونز
    -0.97
     disambiguazione
    -0.82
    verwijspagina
    -0.77
     Bewußt
    -0.77
     kasarigan
    -0.77
     صوتيه
    -0.75
    +#+#
    -0.73
    ngrx
    -0.73
     يتيمه
    -0.72
     متحده
    -0.72
    POSITIVE LOGITS
    ↵↵↵
    0.88
    ↵↵↵↵↵↵↵
    0.81
    ↵↵↵↵↵
    0.78
    ↵↵↵↵
    0.76
    ↵↵↵↵↵↵
    0.75
    <eos>
    0.72
    ↵↵↵↵↵↵↵↵
    0.71
    ↵↵
    0.71
    ↵↵↵↵↵↵↵↵↵
    0.69
    ↵↵↵↵↵↵↵↵↵↵
    0.68
    Activations Density 0.920%

    No Known Activations