© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11880
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and policy discussions

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

    "based on" or "determined by"

    np_acts-logits-general · gemini-2.0-flash

    based on factors or criteria

    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
    AutoField
    -0.56
    hemiah
    -0.54
    SourceChecksum
    -0.53
    rungsseite
    -0.52
     kasarigan
    -0.52
    ipedi
    -0.50
     Meksiku
    -0.49
    DockStyle
    -0.49
    akterysty
    -0.49
    Mutability
    -0.48
    POSITIVE LOGITS
     factors
    1.04
     based
    0.94
     criteria
    0.90
    factors
    0.87
     Factors
    0.87
     dựa
    0.81
    based
    0.80
     baseado
    0.80
    Factors
    0.78
     criterion
    0.77
    Activations Density 0.630%

    No Known Activations