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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3058
    Prev
    Next
    INDEX
    Explanations

    references to counts or quantities in various contexts

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

    "number of"

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with "number of"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SOUNDBITE
    -0.43
     BoxFit
    -0.43
    stool
    -0.43
    decor
    -0.42
    belt
    -0.40
    cosmic
    -0.40
    ègre
    -0.40
    fram
    -0.40
     biraz
    -0.40
    ful
    -0.40
    POSITIVE LOGITS
     počet
    0.85
    getNumberOf
    0.82
     numberOf
    0.82
    NumberOf
    0.81
     antal
    0.81
     noOf
    0.81
     Anzahl
    0.80
     aantal
    0.77
     fewer
    0.75
    numberOf
    0.75
    Activations Density 0.480%

    No Known Activations