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. 24-GEMMASCOPE-RES-16K
    6. 12745
    Prev
    Next
    INDEX
    Explanations

    patterns related to the letter 'c' and its combinations in various contexts

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

    Hexadecimal characters

    np_acts-logits-general · gemini-2.0-flash

    'c' followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.53
    mce
    -0.52
    TagMode
    -0.51
    WebElementEntity
    -0.50
    ništ
    -0.49
    AndroidJUnit
    -0.47
    cú
    -0.47
    rq
    -0.47
    saraba
    -0.47
    φάλ
    -0.46
    POSITIVE LOGITS
    BeginContext
    0.67
     intptr
    0.57
    Източници
    0.54
    FunctionFlags
    0.53
    Pautan
    0.49
    itatem
    0.48
     habitudes
    0.48
    Rohy
    0.47
    原始内容存档于
    0.47
    WebMethod
    0.46
    Activations Density 0.121%

    No Known Activations