© 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. 13217
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and operations involving methods and properties

    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
    íslu
    -0.47
    ")));
    -0.47
    FormTagHelper
    -0.45
    $.}
    -0.44
    __":
    -0.43
     Wier
    -0.42
    TypeService
    -0.42
     evoked
    -0.42
     bells
    -0.41
     przesz
    -0.41
    POSITIVE LOGITS
    replace
    1.01
    split
    0.94
    replaceAll
    0.84
    Replace
    0.80
    toLowerCase
    0.79
    trim
    0.79
     replace
    0.79
    substring
    0.76
    Split
    0.69
     Replace
    0.69
    Activations Density 0.151%

    No Known Activations