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. 2202
    Prev
    Next
    INDEX
    Explanations

    terminology related to intellectual property and copyright law

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

    Followed by "property" or "properties"

    np_acts-logits-general · gemini-2.0-flash

    property

    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
    bootstrapcdn
    -0.67
    webElementXpaths
    -0.65
    انجليز
    -0.64
    хьтан
    -0.64
    __((
    -0.61
     Signalez
    -0.58
    \{\\
    -0.57
    tamol
    -0.57
    EndInit
    -0.56
    первых
    -0.54
    POSITIVE LOGITS
     property
    3.87
    property
    3.41
     Property
    3.36
    Property
    3.17
     PROPERTY
    3.16
     properties
    3.06
     Properties
    2.74
    PROPERTY
    2.73
    properties
    2.64
    Properties
    2.49
    Activations Density 0.264%

    No Known Activations