© 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-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 12422
    Prev
    Next
    INDEX
    Explanations

    structure and formatting elements in HTML or similar markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.57
    AndEndTag
    -0.56
    transQ
    -0.54
    IntoConstraints
    -0.52
    IgnoreCase
    -0.52
     '\\;'
    -0.52
     Constitucional
    -0.52
     Shreve
    -0.51
    ecka
    -0.49
     vivir
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.83
    </em>
    0.73
     }}$}
    0.69
    下载附件
    0.64
    脚注の使い方
    0.62
    ⓘ
    0.60
    .*")]
    0.60
    UnknownFieldSet
    0.59
    </u>
    0.58
    ContentAsync
    0.57
    Activations Density 0.113%

    No Known Activations