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. 360
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight the frequency or occurrence of the word "few."

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

    the phrase "a few".

    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
     Hartman
    -0.48
    GenerationType
    -0.46
     Hartmann
    -0.45
    araman
    -0.42
     Matheson
    -0.40
     is
    -0.39
     BrowserModule
    -0.39
    TGA
    -0.38
     Ис
    -0.38
    return
    -0.38
    POSITIVE LOGITS
    Few
    1.18
     few
    1.18
     FEW
    1.11
    few
    1.07
     Few
    1.05
     wenige
    0.92
     dozen
    0.87
     poucos
    0.84
     wenigen
    0.82
     pocos
    0.78
    Activations Density 0.034%

    No Known Activations