© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10496
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to the concept of "form" and its various applications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    The token "form" and its variations

    np_acts-logits-general · gemini-2.0-flash

    forms and related derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     NCC
    -0.74
    ]++;
    -0.71
     Keegan
    -0.71
    aughter
    -0.70
    FailureListener
    -0.69
     Fische
    -0.69
    ()]
    -0.69
    wyczaj
    -0.67
    ikations
    -0.67
    "])
    -0.67
    POSITIVE LOGITS
     FORM
    1.45
     Forms
    1.32
     Form
    1.28
    form
    1.21
    FORM
    1.21
     FORMS
    1.21
     forms
    1.20
    Form
    1.20
     Forma
    1.17
    forms
    1.12
    Activations Density 0.148%

    No Known Activations