© 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. 4772
    Prev
    Next
    INDEX
    Explanations

    indications of uncertainty or awareness of missing information

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

    Followed by "something" or "like"

    np_acts-logits-general · gemini-2.0-flash

    missing something

    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
    ArrowToggle
    -0.58
    सन्दर्भ
    -0.53
    RegistryLite
    -0.53
    IsPostBack
    -0.52
     Outros
    -0.51
    drawSprites
    -0.51
     ogóle
    -0.50
     Arhivirano
    -0.50
    tır
    -0.49
    sianic
    -0.47
    POSITIVE LOGITS
     something
    4.35
    something
    3.79
    Something
    3.61
     Something
    3.52
     SOMETHING
    2.96
     qualcosa
    2.66
     somethin
    2.57
     quelque
    2.54
     algo
    2.37
     coś
    2.23
    Activations Density 0.470%

    No Known Activations