© 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. 22-GEMMASCOPE-RES-16K
    11. 5703
    Prev
    Next
    INDEX
    Explanations

    terms related to economic impact and community development initiatives

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

    followed by articles or verbs

    np_acts-logits-general · gemini-2.0-flash

    increasing illuminance, tough questions, achieve results, employee, mobile, era

    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
     Roskov
    -0.84
    ...
    -0.66
     snippetHide
    -0.64
    !
    -0.62
    Tikang
    -0.61
    ########.
    -0.60
    ?
    -0.55
    GEBURTSDATUM
    -0.55
    </thead>
    -0.54
     NSCoder
    -0.54
    POSITIVE LOGITS
     This
    0.76
     In
    0.72
     Although
    0.71
     The
    0.70
     These
    0.69
     http
    0.69
     It
    0.69
    ことなく
    0.69
     Besides
    0.67
     https
    0.66
    Activations Density 0.103%

    No Known Activations