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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1801
    Prev
    Next
    INDEX
    Explanations

    terms related to forests and vegetation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -1.05
    tonsoft
    -1.05
    IBarButtonItem
    -1.02
     Viceroy
    -1.00
    LabelTagHelper
    -0.98
     تضيفلها
    -0.96
     ainfi
    -0.94
    Aktualisiert
    -0.93
     payé
    -0.92
     Phari
    -0.92
    POSITIVE LOGITS
     Forest
    1.67
     forest
    1.66
    Forest
    1.56
    forest
    1.47
     forests
    1.29
     FOREST
    1.26
     Forrest
    1.24
    FOREST
    1.20
     Forests
    1.16
    Forrest
    1.16
    Activations Density 0.021%

    No Known Activations