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. 92355
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "another"

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

    signals another instance

    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
     ambientale
    -0.53
     tarko
    -0.52
    ulemon
    -0.51
     picioare
    -0.50
     leeftijd
    -0.49
     høre
    -0.49
     wiedzy
    -0.47
    woordig
    -0.46
    gerufen
    -0.46
     balení
    -0.45
    POSITIVE LOGITS
     another
    1.43
     ANOTHER
    1.30
    another
    1.28
     Another
    1.15
    Another
    1.14
     other
    0.87
     OTHER
    0.85
    Autre
    0.84
    nother
    0.81
    Otra
    0.80
    Activations Density 0.021%

    No Known Activations