© 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. 16-GEMMASCOPE-RES-16K
    11. 6925
    Prev
    Next
    INDEX
    Explanations

    terms related to properties and attributes in both technical and social contexts

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

    preceding "of"

    np_acts-logits-general · gemini-2.0-flash

    social change necessary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.62
    +#+#
    -0.61
    出版年
    -0.56
     utafitiHapana
    -0.56
    はじめに
    -0.56
     كومونز
    -0.56
    ulink
    -0.55
    kově
    -0.55
     становника
    -0.54
    :✨
    -0.53
    POSITIVE LOGITS
     necessary
    0.78
     required
    0.77
    necessary
    0.70
    required
    0.66
     advocated
    0.65
     needed
    0.64
    needed
    0.61
     promised
    0.60
     mentioned
    0.59
     that
    0.58
    Activations Density 0.692%

    No Known Activations