© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104562
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to data retrieval and recording in coding contexts

    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
    s
    -0.52
    áll
    -0.52
    Diffuse
    -0.50
     Felice
    -0.47
    spod
    -0.47
     Merrill
    -0.46
    Leaf
    -0.46
    slf
    -0.46
    Keefe
    -0.44
    Trace
    -0.43
    POSITIVE LOGITS
    getValue
    0.65
    corder
    0.61
     Recorder
    0.61
     currentNode
    0.60
     getValue
    0.60
     jButton
    0.58
    jenigen
    0.57
    er
    0.57
    NUMX
    0.55
    RoutingModule
    0.54
    Activations Density 0.023%

    No Known Activations