© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14095
    Prev
    Next
    INDEX
    Explanations

    instances of the word "corner" and variations of it in various contexts

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

    "corner"

    np_acts-logits-general · gemini-2.0-flash

    corner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.82
    tfrac
    -0.70
     Marlowe
    -0.64
     Shetty
    -0.64
    Holger
    -0.63
    ثر
    -0.63
    Elisa
    -0.62
     PropTypes
    -0.61
     Nak
    -0.61
    dotenv
    -0.61
    POSITIVE LOGITS
     Corner
    0.83
     houſe
    0.81
     Jefus
    0.80
     ']
    0.77
     CORNER
    0.77
     Monfieur
    0.76
    Corner
    0.75
     acet
    0.75
    corners
    0.75
     corners
    0.74
    Activations Density 0.361%

    No Known Activations