© 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. 0-GEMMASCOPE-RES-16K
    6. 9390
    Prev
    Next
    INDEX
    Explanations

    references to children and young individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.89
     فريبيس
    -0.78
     queſta
    -0.77
    ſelf
    -0.77
     resourceCulture
    -0.75
     autorytatywna
    -0.75
    AddTagHelper
    -0.71
     myſelf
    -0.71
    featureID
    -0.69
    ValueStyle
    -0.69
    POSITIVE LOGITS
     kid
    0.75
     free
    0.75
     Free
    0.73
     boys
    0.73
     boy
    0.71
     girl
    0.68
    Free
    0.64
     kids
    0.64
     girls
    0.63
     guy
    0.61
    Activations Density 0.201%

    No Known Activations