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

    Neuronpedia

    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. 4115
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and transport stations

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

    Following prepositions or "user"

    np_acts-logits-general · gemini-2.0-flash

    geographic and directional indicators

    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
    uParam
    -0.36
     препратки
    -0.35
    ngdoc
    -0.35
     threshold
    -0.34
     Exacts
    -0.34
    resizing
    -0.33
    OCCURRED
    -0.32
     transition
    -0.32
     boundary
    -0.32
    idos
    -0.32
    POSITIVE LOGITS
     HttpNotFound
    0.59
     destinations
    0.52
    省市镇
    0.48
     lengthwise
    0.48
     AssemblyCulture
    0.47
    jsonwebtoken
    0.46
    +#+
    0.45
     westward
    0.45
    ็จ
    0.45
     tujuan
    0.45
    Activations Density 0.337%

    No Known Activations