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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14666
    Prev
    Next
    INDEX
    Explanations

    references to cooperation and collaboration in research contexts

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

    Technical or procedural descriptions

    np_acts-logits-general · gemini-2.0-flash

    technical processes and research methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    StoryboardSegue
    -0.89
     ProtoMessage
    -0.79
    DebuggerNonUser
    -0.75
    ineno
    -0.72
    riwal
    -0.69
    ̍t
    -0.67
     externi
    -0.67
     препратки
    -0.66
     Numerade
    -0.65
    LikeLike
    -0.65
    POSITIVE LOGITS
     of
    0.52
     method
    0.47
     system
    0.45
    分
    0.45
     list
    0.44
    gráfica
    0.44
     phẩm
    0.43
    <bos>
    0.42
     szüks
    0.41
     connexes
    0.41
    Activations Density 0.643%

    No Known Activations