© 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. 23-GEMMASCOPE-RES-16K
    6. 14741
    Prev
    Next
    INDEX
    Explanations

    references to visits and visitors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dotenv
    -0.64
    Personendaten
    -0.59
    ConstraintMaker
    -0.57
    aupun
    -0.57
    łgor
    -0.56
     colspan
    -0.55
    setProperty
    -0.54
    είς
    -0.52
     Marcell
    -0.52
     diri
    -0.51
    POSITIVE LOGITS
     kasarigan
    0.81
    expandindo
    0.79
     utafitiHapana
    0.76
    ThroughAttribute
    0.75
    ations
    0.70
    CppMethod
    0.66
    DebuggerNonUser
    0.63
     guid
    0.59
     sumpay
    0.58
    GroupLayout
    0.57
    Activations Density 0.060%

    No Known Activations