© 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. 16-GEMMASCOPE-RES-16K
    11. 13598
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate being out of context or inappropriate situations

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

    "out of"

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with "out of"

    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
    ValueStyle
    -0.83
    出版年
    -0.79
     doInBackground
    -0.79
    DotNetBar
    -0.77
     متعلقه
    -0.74
    Parcelize
    -0.74
     AssemblyCulture
    -0.71
     quæ
    -0.71
     Efq
    -0.68
    DockStyle
    -0.63
    POSITIVE LOGITS
     touch
    0.53
     outta
    0.51
    OutOf
    0.49
     cu
    0.47
     mind
    0.47
     lòng
    0.46
     ung
    0.46
    tamentos
    0.46
    yntaxException
    0.45
    touch
    0.45
    Activations Density 0.100%

    No Known Activations