Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8067
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to mental health and its intersections with various social issues, particularly around sexuality and identity

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

    Text after commas in legal contexts

    np_acts-logits-general · gemini-2.0-flash

    use, copy, modify

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    -0.73
     CanadaChoose
    -0.54
     perfect
    -0.49
    gi
    -0.49
    agam
    -0.46
     crossorigin
    -0.46
     вовсе
    -0.44
     /
    -0.44
    -/
    -0.43
     và
    -0.43
    POSITIVE LOGITS
     Мексичка
    1.13
    +#+#
    0.82
     Paglinawan
    0.79
    NamedQueries
    0.79
     getItemId
    0.78
    bidities
    0.78
     >=",
    0.78
     Efq
    0.77
     "..\..\..\
    0.75
     myſelf
    0.73
    Activations Density 0.258%

    No Known Activations