© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 121969
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and conditions within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    存于互联网档案馆
    -0.51
     OMITBAD
    -0.47
    unzel
    -0.46
     respective
    -0.45
     entirety
    -0.45
     microbiome
    -0.45
    Mű
    -0.45
     prioritize
    -0.43
     lgbt
    -0.43
     LGBTQ
    -0.43
    POSITIVE LOGITS
     muß
    0.56
    faßt
    0.47
     informée
    0.46
     daß
    0.46
    addCriterion
    0.44
     skall
    0.44
     wußte
    0.44
     läßt
    0.43
     obie
    0.43
    AndEndTag
    0.42
    Activations Density 0.307%

    No Known Activations