© 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. 0-GEMMASCOPE-RES-16K
    6. 9978
    Prev
    Next
    INDEX
    Explanations

    references to modules or modular components in the context of programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indígen
    -0.72
     pouvoit
    -0.71
    ChildScrollView
    -0.71
    pecabe
    -0.71
     étoient
    -0.69
     saveiro
    -0.68
     técn
    -0.66
     Geſch
    -0.66
     auroit
    -0.65
     fotográfica
    -0.65
    POSITIVE LOGITS
     Module
    0.56
     module
    0.54
    module
    0.54
    MODULE
    0.52
    Module
    0.50
     unfavorable
    0.46
    goto
    0.45
     PM
    0.45
    Personendaten
    0.43
     как
    0.43
    Activations Density 0.249%

    No Known Activations