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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7727
    Prev
    Next
    INDEX
    Explanations

    HTML and XML markup elements

    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
    Gambas
    -0.54
     scale
    -0.49
     Scale
    -0.46
    OuterClass
    -0.46
     scales
    -0.45
    ociação
    -0.45
    kolwiek
    -0.44
    quíni
    -0.42
     SCALE
    -0.42
     proportional
    -0.41
    POSITIVE LOGITS
     تضيفلها
    0.84
     mergeFrom
    0.67
     дописавши
    0.67
    nodoc
    0.65
    RegistryLite
    0.62
     ModelExpression
    0.61
    findpost
    0.60
    msgSender
    0.58
    Према
    0.58
    JspWriter
    0.57
    Activations Density 0.135%

    No Known Activations