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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5896
    Prev
    Next
    INDEX
    Explanations

    phrases related to error messages and debugging information

    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
     autorytatywna
    -0.49
    cemment
    -0.48
    bolistas
    -0.47
    aternity
    -0.45
     Klass
    -0.45
    NgModule
    -0.43
    Tikang
    -0.42
    lovakia
    -0.42
    RectangleBorder
    -0.42
    Cordialement
    -0.42
    POSITIVE LOGITS
    enderror
    0.53
    FailureListener
    0.45
    MethodManager
    0.42
    verifyException
    0.40
    withOpacity
    0.40
    Démographie
    0.38
     tilbake
    0.38
     tilbage
    0.38
     errores
    0.37
    basicConfig
    0.36
    Activations Density 0.342%

    No Known Activations