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. 8124
    Prev
    Next
    INDEX
    Explanations

    technical terms and attributes related to coding, frameworks, and data validation

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

    Refers to properties, attributes, or fields

    np_acts-logits-general · gemini-2.0-flash

    properties and fields

    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
    contentLoaded
    -0.65
     referenties
    -0.64
     pareti
    -0.64
    selaer
    -0.59
     مرئيه
    -0.59
     tasche
    -0.58
     Principles
    -0.57
    AccessorTable
    -0.57
     foundations
    -0.56
     Chriftian
    -0.56
    POSITIVE LOGITS
     parameter
    1.20
     field
    1.17
     attribute
    1.08
     property
    1.01
     flag
    0.99
     variable
    0.94
    parameter
    0.80
     option
    0.80
     param
    0.79
    field
    0.78
    Activations Density 0.822%

    No Known Activations