© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4654
    Prev
    Next
    INDEX
    Explanations

    elements related to emotional expression and personal experience

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

    medical or scientific research-related topics involving detailed methodological descriptions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    varargin
    -0.38
    antd
    -0.37
     Incre
    -0.36
    endphp
    -0.35
     dead
    -0.35
    Siehe
    -0.34
    お疲れ様でした
    -0.34
    ❊
    -0.34
     Dodson
    -0.34
    SuppressLint
    -0.33
    POSITIVE LOGITS
     typelib
    0.72
     CreateTagHelper
    0.62
    writeFieldEnd
    0.61
    ValueStyle
    0.61
     lisäksi
    0.58
    ⓧ
    0.57
    httphttps
    0.57
    setVerticalGroup
    0.55
     inoltre
    0.53
    HomeAsUpEnabled
    0.52
    Activations Density 0.280%

    No Known Activations