© 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. 14230
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags related to page configuration and character set

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

    HTML or Javascript attributes and declarations

    np_acts-logits-general · gemini-2.0-flash

    initial charset width height

    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
    :✨
    -0.68
     gynhyrchwyd
    -0.59
    unque
    -0.53
     genoux
    -0.52
    rrggbb
    -0.51
    rikan
    -0.49
    itored
    -0.48
    akteur
    -0.46
     endfor
    -0.46
     reichen
    -0.46
    POSITIVE LOGITS
     initial
    0.66
     nahilalakip
    0.63
    initial
    0.58
     Initial
    0.52
     UserRepository
    0.51
    GraphicsUnit
    0.51
     Meksiku
    0.50
    EditorBrowsable
    0.50
    Initial
    0.50
    исленность
    0.49
    Activations Density 0.086%

    No Known Activations