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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5716
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistical values

    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
     the
    -0.40
     opge
    -0.37
     ruok
    -0.35
     herinner
    -0.32
     vraag
    -0.31
     a
    -0.31
    Portale
    -0.31
     adota
    -0.31
     potrzeby
    -0.31
    หาย
    -0.31
    POSITIVE LOGITS
     Monfieur
    0.83
     MainAxisSize
    0.80
    principalColumn
    0.80
    addPreferredGap
    0.77
     betweenstory
    0.75
    tagHelperRunner
    0.73
     Houſe
    0.73
    AnimationsModule
    0.73
     CascadeType
    0.72
    Autoritní
    0.71
    Activations Density 0.679%

    No Known Activations