© 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. 25-GEMMASCOPE-RES-16K
    11. 6538
    Prev
    Next
    INDEX
    Explanations

    sections of code that manage session properties and their configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.81
    Revenir
    -0.80
    RetentionPolicy
    -0.74
     kasarigan
    -0.65
     للاسماء
    -0.63
    ardia
    -0.63
    }],
    -0.62
     Chwiliwch
    -0.62
    UnsafeEnabled
    -0.62
    ädie
    -0.62
    POSITIVE LOGITS
     Dunlop
    0.47
    roves
    0.46
     depends
    0.43
     based
    0.43
     partenza
    0.42
    atrième
    0.41
     temporaire
    0.40
     debout
    0.40
     vorüber
    0.40
    setDo
    0.40
    Activations Density 0.055%

    No Known Activations