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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13709
    Prev
    Next
    INDEX
    Explanations

    references to prominent individuals, specifically Martin Luther King Jr. and related discussions or events

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

    Preceding adjectives or nouns

    np_acts-logits-general · gemini-2.0-flash

    duration of time

    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
    揄
    -0.52
     Pn
    -0.50
    หวัด
    -0.48
    )‏
    -0.46
    /~
    -0.46
     Hn
    -0.45
     ACI
    -0.44
    MetaObject
    -0.44
    rca
    -0.44
     Cm
    -0.44
    POSITIVE LOGITS
     zijne
    0.69
     Wikiseite
    0.69
     Offisielt
    0.68
    printStackTrace
    0.64
     mijne
    0.63
     Ráp
    0.61
     dezelve
    0.60
     ainfi
    0.60
     avoient
    0.60
     feroit
    0.59
    Activations Density 2.241%

    No Known Activations