© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 2109
    Prev
    Next
    INDEX
    Explanations

    narratives surrounding historical events and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Precautionary
    -0.50
     chi̍t
    -0.48
    Rüyada
    -0.44
    сылкі
    -0.42
    wendungs
    -0.40
    rrggbb
    -0.38
     troubleshoot
    -0.38
    ècie
    -0.38
     waitFor
    -0.38
     Réponses
    -0.37
    POSITIVE LOGITS
     historians
    2.02
     historical
    1.84
     historian
    1.77
     histor
    1.72
     Historical
    1.63
    historical
    1.57
    Historical
    1.56
     Histor
    1.53
     Historian
    1.52
     historiador
    1.47
    Activations Density 0.953%

    No Known Activations