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. 19-GEMMASCOPE-RES-16K
    6. 402
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical values and their associated symbols or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chee
    -0.53
     bezeichneter
    -0.52
    cheese
    -0.51
     cheese
    -0.50
    nsis
    -0.49
     Cheese
    -0.48
    setupUi
    -0.46
     الحره
    -0.46
    edenken
    -0.46
    Linda
    -0.45
    POSITIVE LOGITS
    4
    1.46
     Fourth
    1.31
     fourth
    1.22
    Fourth
    1.18
     Four
    1.16
     four
    1.12
    four
    1.10
     FOURTH
    1.07
    fourth
    1.06
     keempat
    1.05
    Activations Density 1.034%

    No Known Activations