© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13816
    Prev
    Next
    INDEX
    Explanations

    phrases related to absence and the passage of time

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

    someone being away or absent

    np_acts-logits-general · gemini-2.0-flash

    absence or being out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jardins
    -0.39
     falschen
    -0.34
     senhor
    -0.32
    adra
    -0.32
    omás
    -0.31
     jazdy
    -0.31
     jeugd
    -0.31
     zweimal
    -0.31
     falsche
    -0.30
     Derecho
    -0.29
    POSITIVE LOGITS
    +#+
    0.66
    出版年
    0.59
    HtmlAttribute
    0.58
    findpost
    0.58
     AssemblyCulture
    0.57
     Infórmanos
    0.56
    addCriterion
    0.56
     ProtoMessage
    0.54
    __':
    0.53
     utafitiHapana
    0.52
    Activations Density 0.229%

    No Known Activations