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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 235
    Prev
    Next
    INDEX
    Explanations

    the presence of contractions and possessive forms

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

    first-person pronouns and possessive words (I, I'm, my, etc.).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ‘
    -0.52
     Umbrella
    -0.50
     –
    -0.50
    та
    -0.49
    }}_{\
    -0.48
    |}{\
    -0.48
    ’,
    -0.47
    <>());
    -0.46
    es
    -0.46
    IFT
    -0.45
    POSITIVE LOGITS
     Bewußt
    0.69
     desmotivaciones
    0.66
    pecabe
    0.65
     computadoras
    0.64
     biß
    0.64
     Wikiseite
    0.63
    wnętr
    0.60
     Paglinawan
    0.60
     fotográfico
    0.59
    actéristi
    0.59
    Activations Density 0.544%

    No Known Activations