© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8747
    Prev
    Next
    INDEX
    Explanations

    references to "corners" in various contexts

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

    "corner" or its variants

    np_acts-logits-general · gemini-2.0-flash

    corners and angular shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ranks
    -0.34
     Ranks
    -0.33
     Mathf
    -0.33
     Re
    -0.33
     ${\
    -0.32
     course
    -0.32
    жд
    -0.32
     }{\
    -0.32
     TType
    -0.32
     An
    -0.32
    POSITIVE LOGITS
     corner
    1.34
     CORNER
    1.23
    corner
    1.22
    Corner
    1.18
     Corner
    1.18
     corners
    1.17
    corners
    1.09
     Corners
    0.97
     esquina
    0.96
     Ecke
    0.89
    Activations Density 0.137%

    No Known Activations