© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 783
    Prev
    Next
    INDEX
    Explanations

    code structures and function definitions related to API requests and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zdjęć
    -0.37
     tertulis
    -0.35
     Wahrnehmung
    -0.35
    Diwedd
    -0.34
     Gehalt
    -0.34
     menangis
    -0.34
     Vordergrund
    -0.32
    spreis
    -0.32
     Hinsicht
    -0.32
     comigo
    -0.32
    POSITIVE LOGITS
     module
    0.79
     domain
    0.69
     compartment
    0.67
     institution
    0.66
     branch
    0.66
    所属
    0.66
     entity
    0.64
     species
    0.64
     group
    0.63
     owner
    0.63
    Activations Density 1.220%

    No Known Activations