© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 9738
    Prev
    Next
    INDEX
    Explanations

    connections or associations between various components or members in a system

    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
     Fourth
    -0.73
    Fourth
    -0.72
    ④
    -0.69
     fourth
    -0.67
     Thursday
    -0.66
     IV
    -0.65
    第四
    -0.63
    Thursday
    -0.62
    FOUR
    -0.62
    fourth
    -0.62
    POSITIVE LOGITS
    +#+#
    0.48
     estekak
    0.47
     protoimpl
    0.47
     Wikime
    0.44
    XtraReports
    0.43
     contextLoads
    0.43
    PostInfinity
    0.42
    MessageTagHelper
    0.42
     հղումներ
    0.41
    Bibliote
    0.40
    Activations Density 0.764%

    No Known Activations