© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7566
    Prev
    Next
    INDEX
    Explanations

    references to corners and their interactions in geometrical or spatial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Buddha
    -0.40
    ~*~
    -0.39
    http
    -0.38
    ✱
    -0.37
     Facebook
    -0.36
     Fiscal
    -0.36
     Tait
    -0.35
    TIM
    -0.35
     Rhyth
    -0.35
     Fost
    -0.35
    POSITIVE LOGITS
     corner
    1.20
     CORNER
    1.19
    Corner
    1.18
     Corner
    1.15
     corners
    1.15
    corner
    1.14
     Corners
    1.13
    corners
    1.05
     esquina
    0.97
    Corners
    0.86
    Activations Density 0.103%

    No Known Activations