Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 69405
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "any" and phrases indicating inclusivity or consideration of various options and conditions

    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
     carottes
    -0.40
    ().__
    -0.36
    fahr
    -0.36
    écution
    -0.36
    viewDidLoad
    -0.36
    ye
    -0.34
    InitStruct
    -0.34
    stepper
    -0.34
    softc
    -0.34
    setContentView
    -0.34
    POSITIVE LOGITS
     eventual
    0.65
     eventuali
    0.63
     Chwiliwch
    0.58
     evtl
    0.57
    archiviato
    0.56
    ⓧ
    0.56
     alterations
    0.56
     évent
    0.55
     eventuell
    0.55
     ensuing
    0.54
    Activations Density 0.026%

    No Known Activations