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-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 10959
    Prev
    Next
    INDEX
    Explanations

    quantitative metrics and measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.64
     مشين
    -0.59
    Autoritní
    -0.57
     تضيفلها
    -0.55
     snippetHide
    -0.54
    ThroughAttribute
    -0.53
    XmlAccessType
    -0.50
     DELLE
    -0.48
    httphttps
    -0.48
    InjectAttribute
    -0.48
    POSITIVE LOGITS
     totaling
    0.81
     totalling
    0.75
     ranging
    0.67
     of
    0.66
     amounting
    0.66
     sebesar
    0.59
     בן
    0.53
     von
    0.53
     equal
    0.53
    ranging
    0.52
    Activations Density 0.590%

    No Known Activations