© 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. 4725
    Prev
    Next
    INDEX
    Explanations

    technical terms related to organization and efficient information management

    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
    >{@
    -0.67
    WebControls
    -0.67
     ExecuteAsync
    -0.63
    httphttps
    -0.62
    ecore
    -0.61
    UrlResolution
    -0.61
    GEBURTSDATUM
    -0.60
    enterOuterAlt
    -0.56
    хьтан
    -0.55
    cosal
    -0.55
    POSITIVE LOGITS
     organized
    2.32
     organize
    2.23
     organizing
    2.19
     organised
    2.11
    organized
    2.08
     Organized
    2.07
     Organize
    2.02
     organizes
    2.02
     Organizing
    2.00
     organise
    1.98
    Activations Density 0.423%

    No Known Activations