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. 1540
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to medical and scientific contexts

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

    Suffixes: cal, defend, Y, tha

    np_acts-logits-general · gemini-2.0-flash

    function calls or abbreviations

    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
    ,
    -0.42
    }
    -0.38
     
    -0.38
    -
    -0.36
     Union
    -0.36
     Community
    -0.35
     avis
    -0.35
    шту
    -0.35
     also
    -0.35
    ordinary
    -0.35
    POSITIVE LOGITS
    uxxxx
    1.08
    boneca
    0.81
     avoient
    0.79
     feroit
    0.77
    transQ
    0.74
     étoient
    0.73
    majánló
    0.72
     vixion
    0.70
    arangay
    0.68
    batore
    0.68
    Activations Density 1.924%

    No Known Activations