Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1240
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strong" and related terms indicating strength or power

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

    Comes after "strong"

    np_acts-logits-general · gemini-2.0-flash

    strong followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exitRule
    -0.56
    CPtr
    -0.54
    JsonPropertyName
    -0.46
     [](
    -0.45
     setTime
    -0.45
     abzu
    -0.44
    [:-
    -0.44
     abz
    -0.44
    [](
    -0.43
    Tembelea
    -0.43
    POSITIVE LOGITS
    strong
    1.31
     strong
    1.25
    Strong
    1.21
     Strong
    1.21
    STRONG
    1.20
     STRONG
    1.17
     strongest
    1.05
     stronger
    1.02
    Strength
    1.00
    strength
    0.98
    Activations Density 0.086%

    No Known Activations