© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11765
    Prev
    Next
    INDEX
    Explanations

    scientific and procedural terms related to processes and operations

    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
    FormTagHelper
    -0.71
    GEBURTSDATUM
    -0.68
    πως
    -0.58
    tagHelperRunner
    -0.58
    RectangleBorder
    -0.57
    новништво
    -0.56
     <<<<<<<<<<<<<<
    -0.55
     विश्वसनीयता
    -0.54
    bufio
    -0.52
    arctan
    -0.51
    POSITIVE LOGITS
     twice
    2.56
     multiple
    2.33
    twice
    2.20
     thrice
    2.07
    multiple
    2.05
     several
    2.05
     numerous
    1.93
     repeatedly
    1.91
     Twice
    1.91
    Twice
    1.88
    Activations Density 0.799%

    No Known Activations