© 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. 7-GEMMASCOPE-RES-16K
    11. 8320
    Prev
    Next
    INDEX
    Explanations

    programming language elements related to visibility and copyright attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.60
     själva
    -0.57
    MigrationBuilder
    -0.54
    <bos>
    -0.51
     rainha
    -0.49
    Teb
    -0.47
    protoimpl
    -0.45
    Gön
    -0.45
     uska
    -0.44
     teto
    -0.43
    POSITIVE LOGITS
     ComVisible
    1.33
     FontWeight
    1.23
    WebControls
    1.12
     typelib
    1.10
     resourceCulture
    1.05
    styleUrls
    0.99
    SqlClient
    0.98
    UIControlState
    0.97
    SBATCH
    0.92
     actionPerformed
    0.91
    Activations Density 0.018%

    No Known Activations