© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27876
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

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

    mathematical notation

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Lähteet
    -0.81
    IntoConstraints
    -0.72
     فريبيس
    -0.70
    DebuggerNonUser
    -0.70
    Hentet
    -0.69
    protoimpl
    -0.66
    ValueStyle
    -0.65
     "..\..\..\
    -0.65
     ***!
    -0.61
    tagHelperRunner
    -0.61
    POSITIVE LOGITS
    thral
    0.57
    \{\\
    0.53
    ölkerung
    0.53
     Zorg
    0.50
     "¿
    0.50
     firent
    0.48
     mourut
    0.48
    osexuality
    0.48
    gevens
    0.47
     Inscrivez
    0.47
    Activations Density 0.125%

    No Known Activations