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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 2301
    Prev
    Next
    INDEX
    Explanations

    phrases related to idiomatic expressions and technical terminology in mathematical or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.21
     Garnish
    -1.01
     Anſ
    -0.96
     Preserve
    -0.95
     raiſ
    -0.95
     Nish
    -0.95
     Shakspeare
    -0.95
     faſt
    -0.94
     Bunt
    -0.93
    reciate
    -0.93
    POSITIVE LOGITS
     Jacobson
    0.84
     Cha
    0.80
    ing
    0.78
    arthur
    0.74
    STON
    0.68
     Somer
    0.67
     Colman
    0.67
     Luna
    0.66
     Jakub
    0.66
     Gros
    0.66
    Activations Density 1.758%

    No Known Activations