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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2588
    Prev
    Next
    INDEX
    Explanations

    instances of image file URLs and options related to downloadable content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gezet
    -0.30
    からです
    -0.30
    ことです
    -0.29
    subplots
    -0.28
     egens
    -0.28
     stat
    -0.27
    ものです
    -0.27
     rép
    -0.26
     DEP
    -0.25
    arrêter
    -0.25
    POSITIVE LOGITS
     nahilalakip
    0.78
    IsMutable
    0.71
    الحياه
    0.66
    DockStyle
    0.64
    forChild
    0.63
    
    0.62
    ंदीखरीदारी
    0.62
     архивлан
    0.60
     betweenstory
    0.60
     Савезне
    0.59
    Activations Density 0.701%

    No Known Activations