© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14436
    Prev
    Next
    INDEX
    Explanations

    references to engineering and construction concepts

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

    Appears before "in"

    np_acts-logits-general · gemini-2.0-flash

    prepositions and conjunctions

    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
     ExecuteAsync
    -0.72
    RenderAtEndOf
    -0.70
    argout
    -0.68
     "..\..\..\
    -0.63
    twimg
    -0.63
    migrationBuilder
    -0.58
     Hệ
    -0.58
    TagHelper
    -0.58
    BeginContext
    -0.55
     @"/
    -0.55
    POSITIVE LOGITS
    blurRadius
    0.51
     embarrassment
    0.50
     front
    0.49
    новниш
    0.48
    ChildScrollView
    0.48
     scolas
    0.46
     adversity
    0.45
     sociala
    0.44
     AudioClip
    0.44
    refour
    0.44
    Activations Density 0.072%

    No Known Activations