© 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. 12-GEMMASCOPE-RES-16K
    6. 13195
    Prev
    Next
    INDEX
    Explanations

    the start of a document or section, as indicated by the presence of specific formatting tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     but
    -0.45
    bkz
    -0.45
     toko
    -0.44
     and
    -0.43
    ごとの
    -0.40
     such
    -0.40
    itoare
    -0.40
    ごとに
    -0.40
    iteurs
    -0.39
     banget
    -0.39
    POSITIVE LOGITS
    contentLoaded
    0.89
    SequentialGroup
    0.85
    ]")]
    0.81
    MessageOf
    0.80
    Personensuche
    0.77
     Baillargeon
    0.77
    FormTagHelper
    0.76
    afficheront
    0.76
    InstanceState
    0.75
    }")]
    0.73
    Activations Density 0.353%

    No Known Activations