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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8135
    Prev
    Next
    INDEX
    Explanations

    code related to GTK tree view interactions and user interface 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
    UrlResolution
    -0.79
     ब्रेकडाउन
    -0.64
    quiao
    -0.58
     snippetHide
    -0.57
     Tape
    -0.54
    exitRule
    -0.53
    maz
    -0.52
    tay
    -0.51
     Eder
    -0.51
    ArgsConstructor
    -0.50
    POSITIVE LOGITS
     gtk
    0.74
     Gtk
    0.73
     GTK
    0.69
     gnome
    0.65
     glade
    0.63
     Gnome
    0.63
    GTK
    0.61
    gtk
    0.59
    Gtk
    0.59
    Gnome
    0.56
    Activations Density 0.574%

    No Known Activations