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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7749
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular processes and signaling molecules involved in growth and immune response

    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
     orçamento
    -0.35
    grà
    -0.35
    kozá
    -0.34
     hands
    -0.33
     Mus
    -0.33
    Intake
    -0.33
     pyta
    -0.33
     dày
    -0.32
     intake
    -0.32
    תר
    -0.32
    POSITIVE LOGITS
     secreted
    0.73
    хьтан
    0.67
     peptide
    0.67
    +#+#
    0.66
     Secre
    0.63
     peptides
    0.63
     secretion
    0.63
    Growth
    0.62
     Peptide
    0.62
     nakalista
    0.61
    Activations Density 1.883%

    No Known Activations