© 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. 2556
    Prev
    Next
    INDEX
    Explanations

    references to collaboration and adaptation in a professional context

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

    trends, changes, or issues

    np_acts-logits-general · gemini-2.0-flash

    market trends and changes

    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
    FormUrlEncoded
    -0.63
    SharedCtor
    -0.61
     Audiodateien
    -0.55
     viewDidLoad
    -0.53
    RenderAtEndOf
    -0.52
    новништво
    -0.52
    itinéraire
    -0.50
    homonymie
    -0.50
    Grath
    -0.49
    omeness
    -0.48
    POSITIVE LOGITS
     trends
    1.79
    trends
    1.44
     Trends
    1.38
     TRENDS
    1.28
     tendances
    1.27
    Trends
    1.26
     trend
    1.24
     changing
    1.19
     changes
    1.16
     tendencias
    1.14
    Activations Density 0.262%

    No Known Activations