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. 16309
    Prev
    Next
    INDEX
    Explanations

    specific information related to health and community programs

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

    usernames or signatures

    np_acts-logits-general · gemini-2.0-flash

    wife, recent, Soviet, var, able

    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
     sahaja
    -0.74
     marvellous
    -0.72
    Obrigada
    -0.70
    theless
    -0.65
    COLOUR
    -0.64
     iaitu
    -0.63
     à
    -0.63
     rhestr
    -0.63
     StatefulWidget
    -0.63
    ohjel
    -0.62
    POSITIVE LOGITS
     ya
    0.67
     Tapatalk
    0.62
     dang
    0.62
     ~$
    0.62
    Wife
    0.60
     مشين
    0.60
    tagHelperRunner
    0.58
     wife
    0.57
     setup
    0.57
    apatalk
    0.56
    Activations Density 0.201%

    No Known Activations