© 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. 38-GEMMASCOPE-RES-16K
    11. 13543
    Prev
    Next
    INDEX
    Explanations

    references to the name "Dan"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.66
     disambiguazione
    -0.66
    LookAnd
    -0.63
    ьажоргаш
    -0.55
     Autorisations
    -0.54
     Италијани
    -0.52
    IUrlHelper
    -0.49
    DockStyle
    -0.49
     připo
    -0.47
     AssemblyCompany
    -0.46
    POSITIVE LOGITS
     Dan
    0.68
     Daniel
    0.65
     DAN
    0.59
    Dan
    0.59
     daniel
    0.54
    DAN
    0.53
     dan
    0.53
    Daniel
    0.53
     DANIEL
    0.52
    delion
    0.51
    Activations Density 0.161%

    No Known Activations