Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10335
    Prev
    Next
    INDEX
    Explanations

    scientific and technical descriptions of natural landscapes and geological features

    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
    tagHelperRunner
    -0.83
    UniformLocation
    -0.67
    TintMode
    -0.62
    ThroughAttribute
    -0.60
    addContainerGap
    -0.57
    PropertyGroup
    -0.57
    fjspx
    -0.57
    esModule
    -0.55
    WebServlet
    -0.55
    WithMany
    -0.54
    POSITIVE LOGITS
    ✨:
    0.64
     pleases
    0.53
     незавершена
    0.52
     Référence
    0.48
     amaze
    0.47
     outwardly
    0.46
    Zunanje
    0.46
    owning
    0.45
     armature
    0.44
    <%@
    0.44
    Activations Density 0.115%

    No Known Activations