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. 16294
    Prev
    Next
    INDEX
    Explanations

    words related to descriptive qualities and states in narratives

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

    [Verb] + with/by/across/near

    np_acts-logits-general · gemini-2.0-flash

    described with spatial prepositions

    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
    PickerController
    -0.69
    UIControlState
    -0.67
    UAGES
    -0.58
     červená
    -0.57
    cienza
    -0.57
    ouflage
    -0.53
     Autorizaciones
    -0.53
    Detalhes
    -0.53
    ilibre
    -0.53
    brido
    -0.52
    POSITIVE LOGITS
    IUrlHelper
    0.93
     variously
    0.77
    BeginContext
    0.69
     nicely
    0.69
    AccessorTable
    0.68
     differently
    0.66
    XmlAccessorType
    0.66
    ly
    0.64
     appropriately
    0.63
     throughout
    0.63
    Activations Density 0.384%

    No Known Activations