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. 17-GEMMASCOPE-RES-16K
    6. 5174
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.59
     Paglinawan
    -0.56
     doInBackground
    -0.56
    ://$
    -0.55
     Вікіпе
    -0.54
    CodeAttribute
    -0.54
    Rptr
    -0.54
     мәкалә
    -0.50
    featureID
    -0.50
    írez
    -0.49
    POSITIVE LOGITS
    それも
    0.79
    这点
    0.71
     виправивши
    0.70
    这一点
    0.67
     */
    
    
    0.62
    XmlAccessType
    0.61
    RTDA
    0.59
     cận
    0.58
    eux
    0.57
     AppCompatTheme
    0.56
    Activations Density 0.506%

    No Known Activations