© 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. 24-GEMMASCOPE-RES-16K
    11. 4680
    Prev
    Next
    INDEX
    Explanations

    terms related to computer games and player interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by software or technology names

    np_acts-logits-general · gemini-2.0-flash

    installing software or tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avoient
    -1.03
     étoient
    -1.01
     feroit
    -0.98
     auroit
    -0.96
     enfans
    -0.93
     stället
    -0.92
     varandra
    -0.91
     étoit
    -0.91
     prêtres
    -0.90
     pouvoit
    -0.89
    POSITIVE LOGITS
     “
    0.31
     the
    0.27
     ‘
    0.26
     
    0.22
     a
    0.21
     either
    0.20
     in
    0.20
     real
    0.20
     and
    0.20
     (
    0.20
    Activations Density 13.908%

    No Known Activations