Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12525
    Prev
    Next
    INDEX
    Explanations

    phrases involving the letter "K"

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

    Tokens followed by "wit" or a period

    np_acts-logits-general · gemini-2.0-flash

    words starting with K

    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
    GEBURTS
    -0.67
    #+#
    -0.65
     nargin
    -0.62
    UMAR
    -0.59
    abestanden
    -0.57
    جوايز
    -0.56
    rawDesc
    -0.55
    +#+
    -0.55
    httphttps
    -0.55
    StoryboardSegue
    -0.54
    POSITIVE LOGITS
    Hz
    0.61
    جغرافيا
    0.47
    olor
    0.46
     SMEs
    0.43
     afield
    0.43
     Icarus
    0.42
    Qq
    0.42
    RV
    0.41
     isotopes
    0.40
    Domaine
    0.40
    Activations Density 0.130%

    No Known Activations