© 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. 16056
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty and assurance

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

    strong affirmation or certainty

    np_acts-logits-general · gemini-2.0-flash

    certainly, definitely, surely, generally, likely

    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
     actually
    -1.37
     basically
    -1.27
     essentially
    -1.26
    actually
    -1.25
     realmente
    -1.20
     apparently
    -1.18
     finalement
    -1.17
     Essentially
    -1.15
     ACTUALLY
    -1.14
     Actually
    -1.14
    POSITIVE LOGITS
     speaking
    0.74
    ities
    0.69
    стям
    0.62
    ঃ
    0.60
     been
    0.60
    ísima
    0.59
    speaking
    0.59
    y
    0.58
    mente
    0.58
     ترین
    0.58
    Activations Density 0.493%

    No Known Activations