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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5616
    Prev
    Next
    INDEX
    Explanations

    error handling and status responses in code

    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
    Билгалдахарш
    -0.51
     CURIAM
    -0.49
    ConstraintMaker
    -0.49
    Décès
    -0.47
     odkazy
    -0.46
    AddTagHelper
    -0.45
     دیکھیے
    -0.45
     sū
    -0.44
    logna
    -0.42
    Биография
    -0.41
    POSITIVE LOGITS
     occhiali
    0.45
     giapp
    0.43
     Kampagne
    0.40
     piatta
    0.39
     griega
    0.38
     mitad
    0.36
    WebVitals
    0.36
     ragazze
    0.36
    msgTypes
    0.36
     meisje
    0.36
    Activations Density 0.902%

    No Known Activations