© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12664
    Prev
    Next
    INDEX
    Explanations

    terms related to financial trades and economic policies

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

    followed by "up", "off", or "out"

    np_acts-logits-general · gemini-2.0-flash

    verbs followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    waitKey
    -0.61
    Portale
    -0.59
    cassert
    -0.58
    ially
    -0.57
    󠁢
    -0.56
    Portail
    -0.56
     estri
    -0.55
    agung
    -0.54
    losigkeit
    -0.54
    Msk
    -0.54
    POSITIVE LOGITS
    outs
    1.30
    offs
    1.23
    out
    1.20
     outs
    1.17
    up
    1.15
    ups
    1.15
     offs
    1.14
    off
    1.12
    down
    1.07
    downs
    1.03
    Activations Density 0.432%

    No Known Activations