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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 47037
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental degradation and species threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    habitat loss and modifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.52
    Cyfeiriadau
    -0.50
    findpost
    -0.49
    sizeCache
    -0.44
    OGND
    -0.43
     архивлан
    -0.41
     становника
    -0.40
    JspWriter
    -0.40
     inval
    -0.40
    PerformLayout
    -0.40
    POSITIVE LOGITS
     habitat
    1.51
    habitat
    1.26
     habitats
    1.24
     Habitat
    1.23
    Habitat
    1.17
     hábitat
    1.10
     Habitats
    0.98
     hábit
    0.94
     habit
    0.89
    habit
    0.88
    Activations Density 0.081%

    No Known Activations