© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7856
    Prev
    Next
    INDEX
    Explanations

    opinions or expressions of agreement and disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IllegalArgument
    -0.52
     Bowman
    -0.51
    assertThrows
    -0.50
    Mediabestanden
    -0.49
    ]='\
    -0.48
    thschild
    -0.46
    ulpt
    -0.46
    photobucket
    -0.46
    odotus
    -0.45
     Siegel
    -0.45
    POSITIVE LOGITS
     незавершена
    0.94
    <bos>
    0.89
    Personendaten
    0.87
     ujednoznacz
    0.75
    titleMargin
    0.69
    ThroughAttribute
    0.69
    LookAnd
    0.68
     mergeFrom
    0.68
    PerformLayout
    0.67
    XmlAccessorType
    0.65
    Activations Density 0.266%

    No Known Activations