© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4447
    Prev
    Next
    INDEX
    Explanations

    HTML markup elements and headers

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

    HTML heading tags (h3, h2, h4, etc.)

    np_acts-logits-general · gemini-2.0-flash

    authoritative or formal language

    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
    Зноскі
    -0.67
     poffible
    -0.60
     fubject
    -0.60
     uſed
    -0.58
     defStyleAttr
    -0.58
    </em>
    -0.56
     newOwner
    -0.54
     Monfieur
    -0.54
    <blockquote>
    -0.53
     nicio
    -0.51
    POSITIVE LOGITS
    Autoritní
    0.69
     виправивши
    0.68
    AxisAlignment
    0.63
    FormTagHelper
    0.63
     autorytatywna
    0.63
     Ts
    0.61
    =$?
    0.60
    AutoScaleMode
    0.60
    "]);
    0.59
    //}
    0.59
    Activations Density 0.045%

    No Known Activations