© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11129
    Prev
    Next
    INDEX
    Explanations

    names of individuals and notable figures

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

    First part of names

    np_acts-logits-general · gemini-2.0-flash

    person names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.67
    setVerticalGroup
    -0.54
    ặt
    -0.46
     similar
    -0.45
    doGet
    -0.45
     housing
    -0.44
    الحياه
    -0.43
    peda
    -0.43
    $")
    -0.42
     stora
    -0.42
    POSITIVE LOGITS
     actionMode
    0.65
     Wiktionnaire
    0.62
    тьяна
    0.61
    InstanceState
    0.60
     Exactos
    0.57
     whips
    0.57
     createSprite
    0.57
     Kennel
    0.56
     estimés
    0.56
     hyperplasia
    0.55
    Activations Density 0.321%

    No Known Activations