© 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. 21-GEMMASCOPE-RES-16K
    6. 3157
    Prev
    Next
    INDEX
    Explanations

    structured programming elements like functions and JSON data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.68
    Ligações
    -0.56
    CreateInfo
    -0.49
     بيها
    -0.48
     roda
    -0.46
     alluminio
    -0.46
    principalColumn
    -0.46
    TabIndex
    -0.45
     CreateTagHelper
    -0.45
     marié
    -0.44
    POSITIVE LOGITS
     Res
    2.14
     res
    2.11
    Res
    2.09
    res
    2.09
     RES
    2.01
    RES
    1.85
     rés
    1.58
     resolution
    1.56
     reso
    1.47
     Rés
    1.44
    Activations Density 0.190%

    No Known Activations