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. 12651
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming syntax and structure within code snippets

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

    Code snippets with "val" or "Val"

    np_acts-logits-general · gemini-2.0-flash

    val and valgus stress

    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
     Taw
    -0.57
     eosin
    -0.53
     AspNetCore
    -0.52
    Rüyada
    -0.49
    SourceChecksum
    -0.49
     ComVisible
    -0.49
     "..\..\
    -0.48
    inhos
    -0.48
    tagHelperRunner
    -0.48
     Camacho
    -0.47
    POSITIVE LOGITS
     val
    3.27
    val
    3.20
     Val
    2.87
    Val
    2.74
    VAL
    2.51
     VAL
    2.49
    vala
    1.65
    valo
    1.60
     vals
    1.55
    vals
    1.54
    Activations Density 0.197%

    No Known Activations