© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12115
    Prev
    Next
    INDEX
    Explanations

    terms related to gas-generating materials and their characteristics

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

    chemical or technical terms related to gas generation, particularly the word "constant" and phrases containing "ant" like "gas generant".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    guenos
    -0.64
     aéro
    -0.59
     Suivez
    -0.58
     obé
    -0.56
     épu
    -0.53
     Houſe
    -0.52
     quæ
    -0.52
     Autres
    -0.51
     auroit
    -0.51
     Theſe
    -0.51
    POSITIVE LOGITS
    ulant
    0.81
    ant
    0.81
    nant
    0.80
    dient
    0.80
    tant
    0.76
    mant
    0.74
    continent
    0.73
    onant
    0.73
    gent
    0.73
    dent
    0.73
    Activations Density 0.356%

    No Known Activations