© 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. 7349
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to forces and interactions in physical systems

    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
    SharedDtor
    -0.53
    enterOuterAlt
    -0.46
    uscita
    -0.43
     resourceCulture
    -0.43
     nakalista
    -0.43
    脚注の使い方
    -0.38
     wait
    -0.37
     sabar
    -0.37
     ček
    -0.37
     переход
    -0.37
    POSITIVE LOGITS
     interaction
    1.88
     interactions
    1.81
    interaction
    1.67
     Interaction
    1.66
     Interactions
    1.63
    Interactions
    1.59
    interactions
    1.59
    Interaction
    1.59
     interacción
    1.43
     interact
    1.37
    Activations Density 1.739%

    No Known Activations