© 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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15886
    Prev
    Next
    INDEX
    Explanations

    components and structures related to React Native programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鼠标
    -0.52
    Портал
    -0.48
     GenerationType
    -0.46
    Portale
    -0.46
    Pfalz
    -0.42
     mouse
    -0.41
     QLabel
    -0.41
     マウス
    -0.41
    المناصب
    -0.40
     ratón
    -0.38
    POSITIVE LOGITS
    StackNavigator
    0.60
     StyleSheet
    0.55
    TouchableOpacity
    0.54
     Android
    0.54
     iOS
    0.54
     NavController
    0.52
     android
    0.52
    Android
    0.49
     getApp
    0.49
     Mobile
    0.49
    Activations Density 0.130%

    No Known Activations