© 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. 25-GEMMASCOPE-RES-16K
    6. 913
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to semiconductor devices and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.54
     وتسجيلات
    -0.48
    roups
    -0.48
    Diwedd
    -0.47
     Isk
    -0.47
    riculum
    -0.45
    PLANATION
    -0.45
     Grun
    -0.45
    jaan
    -0.45
    enada
    -0.44
    POSITIVE LOGITS
     achievable
    0.77
    RegressionTest
    0.69
     (>
    0.68
     attainable
    0.67
     achieved
    0.65
    achie
    0.64
     (<
    0.63
     (~
    0.60
    DockStyle
    0.60
    Achie
    0.58
    Activations Density 2.092%

    No Known Activations