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. 3-GEMMASCOPE-RES-16K
    6. 5878
    Prev
    Next
    INDEX
    Explanations

    technical specifications and numeric data related to measurements or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ICommand
    -0.47
    WaitGroup
    -0.45
    tvguidetime
    -0.44
    SpringBootTest
    -0.43
    NegativeButton
    -0.41
    Portály
    -0.41
    setStroke
    -0.40
    MoveNext
    -0.40
     subgoal
    -0.39
    saveButton
    -0.39
    POSITIVE LOGITS
     Fifteen
    0.70
    Fifteen
    0.70
     Fourteen
    0.70
     fifteen
    0.66
     Eighteen
    0.64
     fifteenth
    0.64
    atorze
    0.63
     fourteen
    0.63
     Sixteen
    0.62
     quinze
    0.61
    Activations Density 0.596%

    No Known Activations