© 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. 10034
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formatting elements related to equations and representing data structures

    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
     number
    -0.89
     ſind
    -0.80
     variety
    -0.79
     InputDecoration
    -0.71
     queſta
    -0.70
    ロウィン
    -0.68
    iſchen
    -0.68
     lot
    -0.68
     stiefe
    -0.67
     few
    -0.66
    POSITIVE LOGITS
     desee
    0.63
     encuentre
    0.49
     løpet
    0.48
     évêque
    0.47
     chrétien
    0.46
    A
    0.45
     politiet
    0.45
     quiera
    0.45
     necesite
    0.44
     apporte
    0.44
    Activations Density 1.647%

    No Known Activations