© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1444
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and functions related to data manipulation and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.77
    帖最后由
    -0.71
    Tikang
    -0.66
    abestanden
    -0.65
    Хьажоргаш
    -0.60
    GEBURTSDATUM
    -0.54
    ("")]
    
    -0.54
    AddHtmlAttribute
    -0.53
    expandindo
    -0.52
     "");
    
    -0.49
    POSITIVE LOGITS
     dė
    0.40
     føl
    0.36
    trzyma
    0.34
     estremamente
    0.34
     aconteceu
    0.33
    quedos
    0.31
     ensued
    0.31
     kandang
    0.31
     stø
    0.31
     aandacht
    0.30
    Activations Density 0.172%

    No Known Activations