© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 16928
    Prev
    Next
    INDEX
    Explanations

    references to detection methods and their comparisons

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

    ELF method for detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    labelledby
    -0.51
    pecabe
    -0.44
     Überblick
    -0.44
     Wikiseite
    -0.43
     Werbung
    -0.42
     désert
    -0.42
     Pineda
    -0.42
    ➌
    -0.42
    Fizz
    -0.41
    utilisons
    -0.41
    POSITIVE LOGITS
    stylers
    0.41
    دانشنامهٔ
    0.41
     سكانية
    0.39
    AnchorStyles
    0.37
     kaarangay
    0.36
    evos
    0.36
     ProtoMessage
    0.35
    InputTagHelper
    0.34
    yarnpkg
    0.34
    ele
    0.33
    Activations Density 0.579%

    No Known Activations