© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104666
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements related to function calls and variable declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.70
    webElementGuid
    -0.69
     transfieras
    -0.68
    +#+
    -0.66
    expandindo
    -0.63
    ItemBackground
    -0.62
     defaultstate
    -0.61
    ſehen
    -0.61
    niſſe
    -0.61
     AssemblyCompany
    -0.60
    POSITIVE LOGITS
      
    0.42
     he
    0.41
    the
    0.41
     The
    0.40
    ,
    0.36
    e
    0.36
    DockStyle
    0.35
    __':
    0.35
    L
    0.34
    it
    0.34
    Activations Density 0.010%

    No Known Activations