© 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. 15-GEMMASCOPE-RES-16K
    6. 12360
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to formal definitions and probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.65
    хьтан
    -0.62
     mapStateToProps
    -0.60
     nakalista
    -0.60
     HasFactory
    -0.59
    ounid
    -0.58
    hmig
    -0.57
    Duplicates
    -0.56
    Földrajzportál
    -0.56
    hilangan
    -0.56
    POSITIVE LOGITS
    ]--;
    0.59
    textTheme
    0.58
     initComponents
    0.58
    TextWatcher
    0.57
    liga
    0.54
     <!--
    0.53
    ciuto
    0.50
     gynnwys
    0.49
    )++;
    0.49
    wezen
    0.49
    Activations Density 0.828%

    No Known Activations