© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105743
    Prev
    Next
    INDEX
    Explanations

    descriptions of beautiful and scenic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Izvori
    -0.58
     primario
    -0.55
     primaire
    -0.54
    replyreport
    -0.53
    criminator
    -0.52
    domada
    -0.50
    ########.
    -0.50
     bezeichneter
    -0.50
     Monfieur
    -0.49
    ſammen
    -0.48
    POSITIVE LOGITS
     scenery
    0.72
     picturesque
    0.65
     scenic
    0.65
     landscapes
    0.59
     beautiful
    0.53
     landscape
    0.52
     Landschaft
    0.50
    beautiful
    0.49
     mountains
    0.49
     surrounding
    0.47
    Activations Density 0.011%

    No Known Activations