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. 14123
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and questions regarding personal experiences or feelings

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

    Japanese sentence ending particles

    np_acts-logits-general · gemini-2.0-flash

    sentence ending particles

    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
    RTDA
    -0.67
    (!__
    -0.60
    AddWithValue
    -0.59
     ModelExpression
    -0.58
     있습니다
    -0.57
    ільки
    -0.55
     SEDS
    -0.54
    uxxxx
    -0.53
    SizeMode
    -0.53
    ktı
    -0.50
    POSITIVE LOGITS
    脚注の使い方
    0.59
    という
    0.59
     AssemblyCulture
    0.58
    라는
    0.56
     싶
    0.56
    ーと
    0.56
    と感じ
    0.55
    と
    0.55
     EconPapers
    0.55
    라고
    0.54
    Activations Density 0.095%

    No Known Activations