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. 24-GEMMASCOPE-RES-16K
    6. 13962
    Prev
    Next
    INDEX
    Explanations

    data structures and elements related to APIs and category management in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code related to objects or data structures

    np_acts-logits-general · gemini-2.0-flash

    Policy followed by Schedule or Owner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .},
    -0.58
    .
    -0.58
    .',
    -0.55
    .')
    -0.52
    .'.
    -0.51
    .",
    -0.51
    .".
    -0.50
    .),
    -0.50
    SharedDtor
    -0.48
    ."),
    -0.48
    POSITIVE LOGITS
     my
    0.78
     true
    0.69
     new
    0.69
     m
    0.68
     this
    0.64
     b
    0.63
     current
    0.63
     p
    0.62
    ParallelGroup
    0.61
     s
    0.61
    Activations Density 0.527%

    No Known Activations