© 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. 8458
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical data or statistics

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

    preceding speech or report attribution

    np_acts-logits-general · gemini-2.0-flash

    officials, parents or speakers say

    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
     Thereafter
    -0.83
     consequent
    -0.79
     Subsequently
    -0.78
     thereby
    -0.76
     concomitant
    -0.75
     („
    -0.73
     thereupon
    -0.73
     (“
    -0.73
     extant
    -0.72
     thereafter
    -0.70
    POSITIVE LOGITS
     FOX
    0.90
    FOX
    0.77
     Tuesday
    0.69
     disini
    0.69
     Officials
    0.67
     Wednesday
    0.65
     Thursday
    0.65
     alright
    0.65
    Tuesday
    0.64
    Officials
    0.64
    Activations Density 0.086%

    No Known Activations