© 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. 24-GEMMASCOPE-RES-16K
    11. 5785
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a noun, often capitalized

    np_acts-logits-general · gemini-2.0-flash

    physical locations and elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.44
     Chwiliwch
    -0.43
     iprot
    -0.39
    fully
    -0.37
    WriteTagHelper
    -0.34
    arry
    -0.33
    hiasan
    -0.32
    SequentialGroup
    -0.32
     הרו
    -0.31
    aute
    -0.31
    POSITIVE LOGITS
    webElementXpaths
    0.79
    IntoConstraints
    0.69
     OMITBAD
    0.59
    endregion
    0.56
    UrlResolution
    0.52
    principalTable
    0.52
    Хьажоргаш
    0.50
    tagHelperRunner
    0.50
    jspb
    0.49
    WEBPACK
    0.48
    Activations Density 0.508%

    No Known Activations