© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3923
    Prev
    Next
    INDEX
    Explanations

    terms related to addiction and drug-related topics

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

    "doi", "dot", "Dop", "Dob", and similar variations

    np_acts-logits-general · gemini-2.0-flash

    words starting with D

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     playera
    -0.35
     Christiansen
    -0.33
     científicas
    -0.31
     vapeur
    -0.31
     Stanton
    -0.31
    ouncing
    -0.30
     Wissenschaftler
    -0.30
     Serbia
    -0.30
    rassing
    -0.30
     Mercier
    -0.30
    POSITIVE LOGITS
     للاسماء
    0.90
    httphttps
    0.84
    rungsseite
    0.82
    Diweddarwch
    0.80
    OGND
    0.79
    ConstraintMaker
    0.78
    Hentet
    0.77
     estekak
    0.76
     فريبيس
    0.76
     Normdatei
    0.74
    Activations Density 0.203%

    No Known Activations