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. 8167
    Prev
    Next
    INDEX
    Explanations

    references to various types of vaccines and their efficacy in combating diseases

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

    before "strategies," "therapy," or "treatment"

    np_acts-logits-general · gemini-2.0-flash

    new medical treatments and therapies

    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
     haunt
    -0.35
    RepeatedField
    -0.32
     telefónica
    -0.31
     suavemente
    -0.31
     Auftrag
    -0.31
     fotográfico
    -0.30
     almendras
    -0.30
     fotográfica
    -0.30
     rallado
    -0.30
     varier
    -0.29
    POSITIVE LOGITS
    InputTagHelper
    0.64
    IUrlHelper
    0.64
     незавершена
    0.60
    doria
    0.53
    agisse
    0.52
    hyrchwyd
    0.52
    AsUp
    0.52
     ſche
    0.51
    uxxxx
    0.51
    idon
    0.51
    Activations Density 0.871%

    No Known Activations