© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 2118
    Prev
    Next
    INDEX
    Explanations

    occurrences of citations, references, and claims about previous research or results in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.74
    featureID
    -0.66
    LookAnd
    -0.64
     Chwiliwch
    -0.63
     Савезне
    -0.63
     चीज़ों
    -0.63
     Administrativna
    -0.63
     Italijanski
    -0.63
    addCriterion
    -0.62
     AssemblyTitle
    -0.59
    POSITIVE LOGITS
     Accordingly
    0.37
     Although
    0.35
     становника
    0.34
     Incidentally
    0.34
    ↵↵
    0.33
     observed
    0.33
    Accordingly
    0.33
    Although
    0.33
    ąb
    0.33
    fikasi
    0.33
    Activations Density 0.856%

    No Known Activations