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. 8483
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components, particularly those related to image and audio handling in programming environments, such as creating instances and setting properties

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

    Code-related initializations

    np_acts-logits-general · gemini-2.0-flash

    objective-c object initialization

    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
     autorytatywna
    -0.66
    elemField
    -0.65
    ⟬
    -0.63
    EndGlobalSection
    -0.62
     noDo
    -0.57
     internetowa
    -0.57
    PreferredItem
    -0.56
     Roskov
    -0.55
     AssemblyTitle
    -0.55
    ">//
    -0.55
    POSITIVE LOGITS
    init
    0.83
     init
    0.68
    نیم
    0.61
     alloc
    0.57
    Init
    0.53
     Init
    0.53
     initWithFrame
    0.51
    INIT
    0.50
    initWithFrame
    0.48
    ゴリー
    0.48
    Activations Density 0.178%

    No Known Activations