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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11967
    Prev
    Next
    INDEX
    Explanations

    words indicating actions, statements, or conditions related to assessment or evaluation

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

    Code, copyright, or identifier-like tokens

    np_acts-logits-general · gemini-2.0-flash

    invention, followed by summary

    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
     briefly
    -1.05
     diligently
    -0.98
     carefully
    -0.94
     selectively
    -0.89
     bravely
    -0.87
     explicitly
    -0.87
     temporarily
    -0.86
    Personendaten
    -0.85
     principally
    -0.85
     mainly
    -0.85
    POSITIVE LOGITS
    saraba
    0.78
     (>
    0.54
    imread
    0.54
    תוך
    0.50
    +#+#
    0.49
    WebServlet
    0.48
    NameInMap
    0.47
     (~
    0.46
    <bos>
    0.45
    ঃ
    0.44
    Activations Density 0.651%

    No Known Activations