© 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. 24-GEMMASCOPE-RES-16K
    11. 10042
    Prev
    Next
    INDEX
    Explanations

    strings containing backslashes and certain formatted text characters

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

    Characters likely before format specifiers

    np_acts-logits-general · gemini-2.0-flash

    newline followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.78
    httphttps
    -0.67
    exitRule
    -0.64
    DoubleQuotes
    -0.57
    енча
    -0.55
    DeleteBehavior
    -0.54
    TagMode
    -0.52
     endforeach
    -0.52
     становника
    -0.49
    CascadeType
    -0.48
    POSITIVE LOGITS
     ujednoznacz
    0.53
     referenties
    0.52
     Penh
    0.51
    Personendaten
    0.47
     utafitiHapana
    0.47
     claiming
    0.47
    InstrumentedTest
    0.47
    IUrlHelper
    0.46
    例句
    0.46
    uger
    0.46
    Activations Density 0.232%

    No Known Activations