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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 23158
    Prev
    Next
    INDEX
    Explanations

    terms related to viability and feasibility

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RepeatedField
    -0.53
     Department
    -0.51
    談社
    -0.50
     its
    -0.49
     Children
    -0.49
     appunt
    -0.48
    Frost
    -0.47
    tag
    -0.47
     Polisi
    -0.47
     Multiplication
    -0.46
    POSITIVE LOGITS
    viable
    0.84
     viable
    0.80
     Viability
    0.77
     viability
    0.74
    asible
    0.71
     Chwiliwch
    0.69
     '\\;'
    0.66
    lihood
    0.65
     feasible
    0.63
    feasible
    0.63
    Activations Density 0.010%

    No Known Activations