© 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. 38-GEMMASCOPE-RES-16K
    11. 9005
    Prev
    Next
    INDEX
    Explanations

    activities and events related to professional gatherings and information dissemination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.35
    かな
    -0.30
    PyObject
    -0.30
     bitte
    -0.28
     '\\;'
    -0.28
     financieras
    -0.28
    ônus
    -0.28
    utico
    -0.28
    에
    -0.27
    useNewUrlParser
    -0.27
    POSITIVE LOGITS
     across
    2.55
     nationwide
    2.31
    across
    2.28
     throughout
    2.27
    Across
    2.22
     Across
    2.19
     everywhere
    2.16
    throughout
    2.14
     ACROSS
    2.03
    everywhere
    1.95
    Activations Density 1.570%

    No Known Activations