© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 9378
    Prev
    Next
    INDEX
    Explanations

    scientific data, particularly related to measurements, percentages, and statistical results

    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
    \{\\
    -0.81
     defaultstate
    -0.55
    thenia
    -0.55
     astore
    -0.53
     AssemblyCulture
    -0.53
    abrigo
    -0.51
    rechnung
    -0.51
    },"
    -0.50
    (/*
    -0.49
    請繼續往下閱讀
    -0.47
    POSITIVE LOGITS
    –
    1.55
     to
    1.40
     až
    1.34
     –
    1.33
    -
    1.31
     -
    1.31
    至
    1.26
    -£
    1.25
     hingga
    1.25
    ~
    1.25
    Activations Density 1.617%

    No Known Activations