© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2221
    Prev
    Next
    INDEX
    Explanations

    terms related to completeness or entirety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ocasião
    -0.50
     Städte
    -0.50
     pájaros
    -0.50
     conductores
    -0.50
     debilidad
    -0.49
     aparcamiento
    -0.48
     Mice
    -0.45
    Mice
    -0.45
     Schick
    -0.45
     jurí
    -0.44
    POSITIVE LOGITS
     Full
    1.32
    Full
    1.27
     full
    1.24
     FULL
    1.17
    FULL
    1.07
    full
    1.05
    isFull
    1.03
     fuller
    0.90
    getFull
    0.88
     fullName
    0.88
    Activations Density 0.078%

    No Known Activations