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. 14339
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance or importance

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

    "important"

    np_acts-logits-general · gemini-2.0-flash

    important followed by significant nouns

    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
     livré
    -0.46
     seleção
    -0.46
     rotina
    -0.46
     vítima
    -0.44
     inscrição
    -0.43
     idéia
    -0.43
    Mô
    -0.42
     calcetines
    -0.42
     galeria
    -0.42
    Morfologia
    -0.42
    POSITIVE LOGITS
    important
    1.19
     Important
    1.16
    Important
    1.14
     important
    1.13
     Importance
    1.04
     importance
    1.02
     importants
    1.01
     importante
    0.98
    IMPORTANT
    0.98
    importante
    0.98
    Activations Density 0.076%

    No Known Activations