© 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. 0-GEMMASCOPE-RES-16K
    11. 9996
    Prev
    Next
    INDEX
    Explanations

    recurring mentions of the word "deck" and the concept of basic principles or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.63
     zijne
    -0.62
    帖最后由
    -0.59
    AndEndTag
    -0.57
     ब्रेकडाउन
    -0.56
     Normdatei
    -0.55
    hassee
    -0.55
    ponses
    -0.55
    ChildScrollView
    -0.54
     errorCode
    -0.53
    POSITIVE LOGITS
     sunset
    0.96
     desc
    0.81
     basic
    0.74
     sunrise
    0.69
     descent
    0.68
    sunset
    0.67
     Sunset
    0.61
     BASIC
    0.58
    Sunset
    0.57
     simple
    0.56
    Activations Density 0.190%

    No Known Activations