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

    Neuronpedia

    Jacobian LensNEW
    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. 0-GEMMASCOPE-RES-16K
    11. 8899
    Prev
    Next
    INDEX
    Explanations

    strings that indicate types or categories in data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Radio
    -0.49
    he
    -0.49
     schwer
    -0.49
     vi
    -0.47
    ddots
    -0.47
    <eos>
    -0.46
    cap
    -0.46
    ')->
    -0.45
    tru
    -0.45
     ام
    -0.45
    POSITIVE LOGITS
    String
    1.06
     String
    1.03
     raiſ
    0.93
    STRING
    0.92
    NSString
    0.92
     againſt
    0.92
    strings
    0.88
    RegressionTest
    0.88
     string
    0.86
    tring
    0.85
    Activations Density 0.143%

    No Known Activations