© 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 - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2861
    Prev
    Next
    INDEX
    Explanations

    terms related to physics and mathematics, particularly in the context of fractional calculus and viscoelasticity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.99
    RenderAtEndOf
    -0.94
    DeleteBehavior
    -0.86
    webElementXpaths
    -0.85
    DockStyle
    -0.83
     >=",
    -0.83
    StoryboardSegue
    -0.81
    MigrationBuilder
    -0.80
     Roskov
    -0.79
     мәкал
    -0.79
    POSITIVE LOGITS
     
    0.47
    ,
    0.44
     fat
    0.43
     am
    0.42
     Fat
    0.41
     cerveau
    0.40
    -
    0.39
    سر
    0.39
    :
    0.39
    fat
    0.39
    Activations Density 2.504%

    No Known Activations