© 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. 8408
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical properties or measures

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

    "des" followed by "criptive" in Java code

    np_acts-logits-general · gemini-2.0-flash

    descriptive statistics

    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
     Hig
    -0.73
     Fairchild
    -0.73
     Krug
    -0.71
     Talis
    -0.70
     Rudi
    -0.69
     Musa
    -0.68
     Elise
    -0.66
     Pulse
    -0.65
     Duch
    -0.65
     Hutchins
    -0.64
    POSITIVE LOGITS
     Greenway
    0.74
     Philly
    0.65
    ivably
    0.65
     Phipps
    0.64
     Ashby
    0.64
     Newberry
    0.63
     Davie
    0.63
     Erl
    0.63
     Schatz
    0.62
     Garrick
    0.61
    Activations Density 0.774%

    No Known Activations