Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 6276
    Prev
    Next
    INDEX
    Explanations

    elements related to collaborative performance and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ății
    -0.42
    клопе
    -0.41
     oog
    -0.40
    結
    -0.40
    assination
    -0.40
     coś
    -0.39
    EXCLUSIVE
    -0.38
     comune
    -0.38
     mats
    -0.37
     window
    -0.37
    POSITIVE LOGITS
    oneofs
    0.89
    存于互联网档案馆
    0.81
    djangoproject
    0.77
    NameInMap
    0.74
    通販
    0.71
    bootstrapcdn
    0.71
     AssemblyCompany
    0.69
    DECREF
    0.69
    цезда
    0.69
     للمعارف
    0.68
    Activations Density 0.145%

    No Known Activations