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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15266
    Prev
    Next
    INDEX
    Explanations

    phrases related to spatial positioning or directionality

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

    "Along" followed by "the" or "a"

    np_acts-logits-general · gemini-2.0-flash

    along a path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assertNull
    -0.50
    openhauer
    -0.43
     Receptor
    -0.43
     Mastercard
    -0.42
     Cryptocurrency
    -0.42
     étrangers
    -0.41
     receptor
    -0.41
     couteau
    -0.41
     Majefty
    -0.41
     destructor
    -0.41
    POSITIVE LOGITS
     along
    0.94
     ALONG
    0.90
    along
    0.85
     Along
    0.84
    Along
    0.83
     ACROSS
    0.63
     Junto
    0.61
     among
    0.61
    across
    0.60
     AMONG
    0.60
    Activations Density 0.115%

    No Known Activations