© 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. 14-GEMMASCOPE-RES-16K
    6. 7342
    Prev
    Next
    INDEX
    Explanations

    phrases related to addiction treatment and support resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     _('
    -0.65
     acrylique
    -0.65
    <>("
    -0.60
     oignon
    -0.58
    '&:
    -0.58
     skog
    -0.57
     Hoe
    -0.56
    ="?
    -0.55
     fogo
    -0.55
    getBytes
    -0.55
    POSITIVE LOGITS
     متعلقه
    0.97
     مشين
    0.95
     للمعارف
    0.94
     وتسجيلات
    0.93
    </caption>
    0.81
     Audiodateien
    0.80
    BeginInit
    0.79
     שוליים
    0.79
    
    0.78
    енча
    0.77
    Activations Density 0.027%

    No Known Activations