© 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. 12-GEMMASCOPE-RES-16K
    11. 14204
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section marker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron strongly activates for the beginning-of-sequence token (i.e., the start of a new input), signaling the start of a document/input.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    requestCode
    -0.50
    RectangleBorder
    -0.49
     requestCode
    -0.47
    iomanip
    -0.47
    شوف
    -0.47
    ētu
    -0.46
    templateUrl
    -0.46
     TAMBÉM
    -0.45
     ListTile
    -0.45
    Eloquent
    -0.42
    POSITIVE LOGITS
    afficheront
    1.32
    GEBURTSDATUM
    1.31
    NameInMap
    1.27
     disambiguazione
    1.23
     ProtoMessage
    1.20
     utafitiHapana
    1.17
    webElementXpaths
    1.16
    RegressionTest
    1.12
    MigrationBuilder
    1.11
    rungsseite
    1.11
    Activations Density 0.526%

    No Known Activations