Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15623
    Prev
    Next
    INDEX
    Explanations

    phrases related to methods of formulation and preparation, particularly regarding gas-generating agents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astéroïdes
    -0.43
     padi
    -0.37
     XCTest
    -0.36
     endforeach
    -0.35
     markets
    -0.34
    вов
    -0.34
     rule
    -0.34
     الوطنيه
    -0.34
    CloseOperation
    -0.33
    karen
    -0.33
    POSITIVE LOGITS
     combinations
    0.61
     initComponents
    0.60
     assemblage
    0.60
    enterOuterAlt
    0.59
     sesta
    0.59
     assemblages
    0.57
     montagem
    0.57
     setups
    0.57
     outfit
    0.56
     구성
    0.56
    Activations Density 0.998%

    No Known Activations