© 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. 15409
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need for more detailed information or elaboration

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

    Following intensifiers such as "more" or "much"

    np_acts-logits-general · gemini-2.0-flash

    more detail

    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
    +#+#
    -0.83
    IVEREF
    -0.65
     виправивши
    -0.62
    IntoConstraints
    -0.59
    styleable
    -0.59
    aarrggbb
    -0.58
     jspb
    -0.58
    makeConstraints
    -0.58
    ActionCreators
    -0.57
    TestingModule
    -0.55
    POSITIVE LOGITS
     detail
    3.56
     details
    3.32
    detail
    3.08
     Detail
    3.06
    details
    2.87
     Details
    2.86
    Detail
    2.82
     DETAIL
    2.79
    Details
    2.64
     détails
    2.63
    Activations Density 0.378%

    No Known Activations