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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 12130
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.59
    SequentialGroup
    -0.54
     yii
    -0.52
    原始内容存档于
    -0.52
    getMenuInflater
    -0.50
    enciaga
    -0.50
    aurait
    -0.50
    oriasis
    -0.49
     Audiodateien
    -0.49
    orghini
    -0.49
    POSITIVE LOGITS
    الإنجليزية
    0.62
     EconPapers
    0.62
     $#
    0.55
    таратура
    0.53
     importância
    0.52
    的原因
    0.49
     صوتيه
    0.48
    WebControls
    0.48
    extAlignment
    0.48
     Auft
    0.47
    Activations Density 0.195%

    No Known Activations