© 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. 4-GEMMASCOPE-RES-16K
    6. 15346
    Prev
    Next
    INDEX
    Explanations

    words related to generating or producing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPATH
    -0.71
    ança
    -0.65
     perjuangan
    -0.63
     ControllerBase
    -0.63
     équilibre
    -0.62
     statusCode
    -0.60
    onAttach
    -0.59
     Alcott
    -0.59
    setInt
    -0.57
     affari
    -0.57
    POSITIVE LOGITS
     Generates
    2.01
     generated
    2.00
     generate
    1.98
     generates
    1.97
     Generate
    1.96
     generating
    1.96
     Generated
    1.92
    generate
    1.90
    Generate
    1.80
    Generating
    1.73
    Activations Density 0.086%

    No Known Activations