© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4217
    Prev
    Next
    INDEX
    Explanations

    terms related to flat and planar structures

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

    flatness or flattening

    np_acts-logits-general · gemini-2.0-flash

    flat and planar shapes

    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
    WriteAttribute
    -0.44
    SqlClient
    -0.43
    JoinColumn
    -0.39
    DrawerToggle
    -0.38
     voegen
    -0.38
    joint
    -0.38
    انتهای
    -0.36
     Vign
    -0.35
     memegang
    -0.35
    joints
    -0.35
    POSITIVE LOGITS
     flat
    0.89
     FLAT
    0.80
    Flat
    0.78
    flat
    0.76
     flattening
    0.75
     flatten
    0.74
     Flat
    0.73
     flattened
    0.73
    Flatten
    0.64
     flats
    0.62
    Activations Density 0.613%

    No Known Activations