© 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. 1350
    Prev
    Next
    INDEX
    Explanations

    references to recommendations or outcomes related to research methodology and evaluations

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

    Followed by a word indicating necessity or recommendation

    np_acts-logits-general · gemini-2.0-flash

    court/research followed by should/must

    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
     beginnetje
    -0.75
    AddTagHelper
    -0.64
    Clik
    -0.63
    findpost
    -0.62
     PagesJaunes
    -0.62
    actéristique
    -0.61
    ごちそうさまでした
    -0.60
    "}"
    -0.59
    Pautan
    -0.58
    Personendaten
    -0.58
    POSITIVE LOGITS
     should
    2.08
    should
    1.74
     Should
    1.67
    Should
    1.65
     SHOULD
    1.43
     must
    1.40
     shouldn
    1.33
    ควร
    1.30
     ought
    1.29
    hould
    1.27
    Activations Density 0.586%

    No Known Activations