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. 2409
    Prev
    Next
    INDEX
    Explanations

    references to telephone hardware and its functionalities

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

    Telephone-related hardware/services

    np_acts-logits-general · gemini-2.0-flash

    telephone calls and equipment

    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
    IsContent
    -0.64
     BoxFit
    -0.57
    MLLoader
    -0.55
    calaureate
    -0.53
    RefreshLayout
    -0.51
    setVerticalGroup
    -0.49
    Neder
    -0.49
     للمعارف
    -0.47
    errHandler
    -0.47
     propOrder
    -0.46
    POSITIVE LOGITS
     call
    0.99
     Calling
    0.96
     calling
    0.95
     calls
    0.93
     Call
    0.93
     Voice
    0.92
     caller
    0.91
    Call
    0.91
     voice
    0.90
     Caller
    0.90
    Activations Density 0.261%

    No Known Activations