© 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. 2450
    Prev
    Next
    INDEX
    Explanations

    references to grants, funding, or financial support in research contexts

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

    Code snippets and programming elements

    np_acts-logits-general · gemini-2.0-flash

    grant, alter, Farr, infty

    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
    EDES
    -0.54
     Volume
    -0.52
    istible
    -0.52
     volume
    -0.51
     CHtml
    -0.51
     Mede
    -0.50
    Volume
    -0.48
    apal
    -0.48
     Tip
    -0.48
    Bell
    -0.47
    POSITIVE LOGITS
     BorderRadius
    0.69
     contextLoads
    0.60
     CreateTagHelper
    0.60
     Normdatei
    0.56
    الصفحه
    0.55
    findpost
    0.54
    RetentionPolicy
    0.52
    enguaje
    0.52
    ConstraintMaker
    0.50
     Infórmanos
    0.50
    Activations Density 0.167%

    No Known Activations