© 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. 18-GEMMASCOPE-RES-16K
    11. 2894
    Prev
    Next
    INDEX
    Explanations

    references to characters and their abilities in a fantasy context

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

    the word "land"

    np_acts-logits-general · gemini-2.0-flash

    strength and power

    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
     ModelExpression
    -0.97
     initComponents
    -0.82
    __':
    -0.74
    HtmlAttribute
    -0.73
    yntaxException
    -0.73
     betweenstory
    -0.72
    didSet
    -0.71
     disambiguazione
    -0.69
    __":
    -0.69
    ">//
    -0.67
    POSITIVE LOGITS
     strength
    0.86
     Strength
    0.73
    Strength
    0.70
    strength
    0.69
     strengths
    0.67
     stronger
    0.65
    实力
    0.64
     strongest
    0.61
     STRENGTH
    0.60
     Stronger
    0.59
    Activations Density 0.137%

    No Known Activations