© 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. 11476
    Prev
    Next
    INDEX
    Explanations

    mentions of well-known comic book franchises and their related films

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

    nouns and compound terms that represent specific entities, products, or technical concepts.

    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
    <bos>
    -0.92
    𝓵
    -0.65
    𝓲
    -0.63
    𝓮
    -0.61
    𝓴
    -0.60
    𝓭
    -0.59
    𝓸
    -0.59
    𝓱
    -0.57
     []:
    -0.56
    𝓿
    -0.55
    POSITIVE LOGITS
    s
    1.74
    ים
    0.98
    ات
    0.75
    ς
    0.71
    sted
    0.67
    ième
    0.61
    ities
    0.58
    ships
    0.56
    iterranean
    0.56
    stanbul
    0.56
    Activations Density 2.225%

    No Known Activations