© 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. 1360
    Prev
    Next
    INDEX
    Explanations

    specific programming concepts and terminology related to functionality and operations within code

    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
     they
    -0.66
     themselves
    -0.61
    reportWebVitals
    -0.58
     itself
    -0.57
    κέ
    -0.56
     Itself
    -0.56
    parseColor
    -0.54
     بگیر
    -0.54
    drawiam
    -0.54
     your
    -0.54
    POSITIVE LOGITS
     ourselves
    1.73
     we
    1.44
    我們
    1.17
     We
    1.14
    我们
    1.12
    We
    1.09
     our
    1.06
    我们在
    1.03
     kami
    1.02
     nous
    1.00
    Activations Density 0.029%

    No Known Activations