Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 3762
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to authors and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Aiheesta
    -0.79
    ThroughAttribute
    -0.77
     שוליים
    -0.74
    iseite
    -0.66
    ]--;
    -0.64
     itſelf
    -0.64
     kaynağından
    -0.64
    Legături
    -0.63
    ínez
    -0.62
    下载附件
    -0.61
    POSITIVE LOGITS
    bootstrapcdn
    0.57
    Indented
    0.53
    belea
    0.42
    urbo
    0.41
     deportivos
    0.41
    Zunanje
    0.40
    bose
    0.40
    XmlEnum
    0.39
     taraf
    0.38
     Solid
    0.38
    Activations Density 0.465%

    No Known Activations