© 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. 10973
    Prev
    Next
    INDEX
    Explanations

    elements of dialogue and expression in various contexts

    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
    <bos>
    -0.59
    preferred
    -0.55
     IndexError
    -0.55
     ComVisible
    -0.54
    TagMode
    -0.53
    œurs
    -0.53
     KeyError
    -0.53
    BuilderFactory
    -0.52
    getRuntime
    -0.52
     determinado
    -0.52
    POSITIVE LOGITS
    THING
    1.04
     everything
    0.93
     things
    0.92
     thing
    0.92
    everything
    0.88
     stuff
    0.88
     THING
    0.87
    thing
    0.86
     Everything
    0.83
     Thing
    0.82
    Activations Density 0.429%

    No Known Activations