© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 1944
    Prev
    Next
    INDEX
    Explanations

    PHP and Yii framework-related code snippets

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

    Yii framework code or related terms

    np_acts-logits-general · gemini-2.0-flash

    Yii framework, ActiveRecord

    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
    UseVisualStyle
    -0.62
    eniendo
    -0.59
    printStackTrace
    -0.59
    tvguidetime
    -0.58
    BeginInit
    -0.58
    脚注の使い方
    -0.58
    addGap
    -0.57
     Tripura
    -0.57
    ueuse
    -0.56
     savons
    -0.56
    POSITIVE LOGITS
    Yii
    0.73
     yii
    0.71
     Yii
    0.69
    yii
    0.64
    gii
    0.62
     Tehran
    0.59
    behaviors
    0.55
    ActiveRecord
    0.53
     Iranian
    0.52
    Active
    0.52
    Activations Density 0.024%

    No Known Activations