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. 4342
    Prev
    Next
    INDEX
    Explanations

    abbreviations and initials, particularly those related to authors and academics

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

    Capital letters followed by lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    names with initials

    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
    One
    -0.43
     financières
    -0.42
    ↵
    -0.42
    lucene
    -0.41
     sanitaires
    -0.41
    -
    -0.40
     tepat
    -0.39
     skj
    -0.38
     especializados
    -0.38
     (
    -0.38
    POSITIVE LOGITS
     Normdatei
    0.85
     referenties
    0.81
    .)}
    0.81
    脚注の使い方
    0.80
     GenerationType
    0.80
     MenuView
    0.73
    IsMutable
    0.73
    HomeAsUpEnabled
    0.72
     فريبيس
    0.71
    .";
    
    0.71
    Activations Density 0.268%

    No Known Activations