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. 8644
    Prev
    Next
    INDEX
    Explanations

    elements of code related to user interface components in programming

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

    Kotlin or Swift code snippets

    np_acts-logits-general · gemini-2.0-flash

    variable and property declarations

    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
     ब्रेकडाउन
    -0.83
    ValueStyle
    -0.82
    SourceChecksum
    -0.80
    findpost
    -0.80
    fjspx
    -0.77
     "..\..\..\
    -0.76
     Roskov
    -0.76
     protoimpl
    -0.76
    GEBURTSDATUM
    -0.75
     समीक्षाओं
    -0.74
    POSITIVE LOGITS
    val
    1.09
     val
    1.01
     Val
    0.72
    VAL
    0.69
    Val
    0.67
    !
    0.62
    vale
    0.55
     VAL
    0.53
     var
    0.50
    !!
    0.50
    Activations Density 0.134%

    No Known Activations