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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1093
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "for" in various contexts

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

    "For" keyword, often in code or religious texts

    np_acts-logits-general · gemini-2.0-flash

    for loop, example, forlorn, forager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createState
    -0.96
    audiovisuel
    -0.78
    enumi
    -0.72
     muualla
    -0.72
     متعلقه
    -0.71
    indelijk
    -0.70
    ิมพ์
    -0.69
     pageContext
    -0.69
    HasAnnotation
    -0.69
    Diwedd
    -0.68
    POSITIVE LOGITS
     For
    1.08
     FOR
    1.07
    FOR
    0.99
    For
    0.97
    for
    0.85
     example
    0.84
     for
    0.74
     voor
    0.67
     reasons
    0.66
    ForValue
    0.66
    Activations Density 0.166%

    No Known Activations