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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14016
    Prev
    Next
    INDEX
    Explanations

    expressions and statements related to conflict and combat, particularly in the context of wrestling or mixed martial arts

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

    Following punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    when certain entities or events occur

    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
    RegistryLite
    -0.53
    RegressionTest
    -0.48
     المعيارى
    -0.47
     promotion
    -0.46
    chit
    -0.45
     виправивши
    -0.45
    ích
    -0.45
     autonome
    -0.45
    orang
    -0.44
     promoters
    -0.44
    POSITIVE LOGITS
     '\\;'
    0.80
    CodeAttribute
    0.61
     Theory
    0.61
     Humberto
    0.59
    Theory
    0.55
     Smack
    0.54
    getMenuInflater
    0.54
     SDLK
    0.53
    StandardCharsets
    0.53
     Natal
    0.53
    Activations Density 0.140%

    No Known Activations