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. 9-GEMMASCOPE-RES-16K
    6. 8929
    Prev
    Next
    INDEX
    Explanations

    references to dust and debris within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    particles and debris like dust, dirt, mud, and grime in physical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.53
    сылкі
    -0.46
    IntoConstraints
    -0.46
     Autorizaciones
    -0.44
    ConstraintMaker
    -0.44
    fromnode
    -0.42
    blox
    -0.42
    Personendaten
    -0.41
     commerciales
    -0.41
     betweenstory
    -0.41
    POSITIVE LOGITS
     dust
    1.02
    Dust
    0.87
     DUST
    0.82
     Dust
    0.82
    dust
    0.80
     poussière
    0.73
     splash
    0.66
     splashes
    0.65
     splashing
    0.63
     dusty
    0.61
    Activations Density 0.424%

    No Known Activations