© 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. 14568
    Prev
    Next
    INDEX
    Explanations

    references to entities or concepts in various contexts

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

    Possessive pronouns followed by a descriptive adjective

    np_acts-logits-general · gemini-2.0-flash

    described in full

    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
    WebElementEntity
    -0.73
    tvguidetime
    -0.72
    afficheront
    -0.69
    ագրություններ
    -0.68
    Билгалдахарш
    -0.67
    Примітки
    -0.67
     typelib
    -0.66
     InputDecoration
    -0.65
    Referanser
    -0.64
    awtextra
    -0.64
    POSITIVE LOGITS
     entirety
    0.74
     completos
    0.71
     completas
    0.61
    følgelig
    0.57
     complete
    0.56
     completo
    0.55
    Forms
    0.52
     totality
    0.51
     its
    0.51
     full
    0.50
    Activations Density 0.149%

    No Known Activations