© 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. 16-GEMMASCOPE-RES-16K
    11. 5849
    Prev
    Next
    INDEX
    Explanations

    decimal points or punctuation in numerical contexts

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

    Code snippets with numpy arrays using `.stack`, `.unique`, or `.array`

    np_acts-logits-general · gemini-2.0-flash

    numpy array operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.81
    ContentAlignment
    -0.78
     betweenstory
    -0.77
    __":
    -0.71
    hasMoreElements
    -0.71
    apimachinery
    -0.71
     itſelf
    -0.68
    Földrajzportál
    -0.68
    MergeFrom
    -0.68
    cinogenicity
    -0.66
    POSITIVE LOGITS
     MonoBehaviour
    0.65
     (_.
    0.65
    miento
    0.60
    )$_
    0.59
     (!__
    0.56
     *
    0.56
     ευ
    0.56
    xia
    0.55
     Pha
    0.53
    ).__
    0.53
    Activations Density 0.062%

    No Known Activations