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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4800
    Prev
    Next
    INDEX
    Explanations

    structural or syntactical elements in programming code, particularly in relation to table views and arrays

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

    Code syntax, especially after "text" or "."

    np_acts-logits-general · gemini-2.0-flash

    Swift, Objective-C, math code

    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
     AssemblyCulture
    -0.72
    LookAnd
    -0.69
    WriteTagHelper
    -0.68
    ImageContext
    -0.67
    AddTagHelper
    -0.64
     خارجية
    -0.64
     препратки
    -0.63
    ConstraintMaker
    -0.63
     NSCoder
    -0.61
    tadır
    -0.60
    POSITIVE LOGITS
    usakan
    0.48
    ########.
    0.47
    subfigure
    0.43
    mj
    0.41
     James
    0.41
    ต้น
    0.41
    old
    0.41
     beras
    0.41
    itoba
    0.41
     Malden
    0.40
    Activations Density 0.188%

    No Known Activations