Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 4529
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nau
    -0.46
    amt
    -0.46
    ances
    -0.42
     lits
    -0.42
     resourceful
    -0.41
    ToolStripButton
    -0.41
     Ans
    -0.40
     convo
    -0.40
     Tony
    -0.39
    ilda
    -0.39
    POSITIVE LOGITS
     فريبيس
    1.16
    LookAnd
    1.13
    #+#
    1.01
    ArrowToggle
    1.01
     Italijanski
    1.01
     estekak
    1.00
    EndGlobalSection
    0.93
     Италијани
    0.92
    WithIOException
    0.92
    QMetaType
    0.91
    Activations Density 1.504%

    No Known Activations