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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11434
    Prev
    Next
    INDEX
    Explanations

    devices and instruments related to measurement and control systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.53
     farsi
    -0.44
    '}>
    -0.44
    '}}>
    -0.42
     φύ
    -0.42
    ']],
    -0.42
    짓
    -0.41
     prem
    -0.41
    </>
    
    -0.40
     Chill
    -0.40
    POSITIVE LOGITS
    MLLoader
    0.64
    ähteet
    0.60
     mikrofon
    0.57
    InputTagHelper
    0.56
    UrlResolution
    0.55
     OkHttpClient
    0.54
     Telescope
    0.53
     ainfi
    0.52
    Máy
    0.52
     device
    0.51
    Activations Density 1.279%

    No Known Activations