© 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. 3-GEMMASCOPE-RES-16K
    6. 5557
    Prev
    Next
    INDEX
    Explanations

    references to roads and corners

    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
    Pranala
    -0.40
     StatefulWidget
    -0.36
     detailsNormal
    -0.36
    áculos
    -0.35
    BrowserModule
    -0.35
    épendance
    -0.34
    ConstraintMaker
    -0.34
     IBOutlet
    -0.33
     sürü
    -0.33
     Prou
    -0.33
    POSITIVE LOGITS
     downstream
    0.86
     downhill
    0.65
     upstream
    0.59
     Upstream
    0.59
    Upstream
    0.58
     downstairs
    0.57
    upstream
    0.56
     adelante
    0.50
    KommentareTeilen
    0.50
    ########.
    0.49
    Activations Density 0.177%

    No Known Activations