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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4839
    Prev
    Next
    INDEX
    Explanations

    formal or structured language associated with legal or technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.62
     հղումներ
    -0.60
     kasarigan
    -0.57
    󠁢
    -0.56
    󠁣
    -0.53
    FTFY
    -0.51
     noqa
    -0.49
    ContentLoaded
    -0.48
     Lage
    -0.47
    oriam
    -0.47
    POSITIVE LOGITS
    uxxxx
    0.59
     Италијани
    0.56
    VYMaps
    0.54
    :✨
    0.46
    oa̍t
    0.44
    ➯
    0.42
    Aholisi
    0.40
     '../../../../
    0.38
    Хьажоргаш
    0.37
     JADX
    0.36
    Activations Density 0.140%

    No Known Activations