© 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. 14-GEMMASCOPE-RES-16K
    11. 645
    Prev
    Next
    INDEX
    Explanations

    terms indicating uniqueness or originality

    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
     Mors
    -0.66
     censura
    -0.65
    <code>
    -0.62
     IMDG
    -0.58
    ütü
    -0.58
    </em>
    -0.57
    Bbb
    -0.57
    BlockPos
    -0.57
    стма
    -0.57
     Barbour
    -0.57
    POSITIVE LOGITS
     UNIQUE
    1.02
    UniqueId
    1.00
    UNIQUE
    0.96
     uniqu
    0.95
     uniques
    0.95
    unique
    0.88
     Unique
    0.87
    uniq
    0.86
    quely
    0.84
    ividual
    0.82
    Activations Density 0.076%

    No Known Activations