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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6318
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "how to" related to performing various tasks or functions

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

    Follows "How to" (or translations of "How to")

    np_acts-logits-general · gemini-2.0-flash

    how to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -0.42
    endios
    -0.41
     belangrij
    -0.39
    icanos
    -0.39
     faptul
    -0.37
     względu
    -0.37
     dachte
    -0.36
     companhia
    -0.36
     instituição
    -0.36
    Données
    -0.35
    POSITIVE LOGITS
    howto
    0.93
     كيفية
    0.61
     如何
    0.60
    Cách
    0.59
    如何
    0.59
     Cách
    0.58
     Cómo
    0.57
     cómo
    0.56
     canst
    0.56
    Рецепт
    0.55
    Activations Density 0.149%

    No Known Activations