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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8358
    Prev
    Next
    INDEX
    Explanations

    instances of possessive apostrophes indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.95
     ſte
    -0.87
     myſelf
    -0.83
     ſta
    -0.80
     Monfieur
    -0.78
     kasarigan
    -0.77
     juſ
    -0.77
     Reſ
    -0.76
     purpoſe
    -0.75
     ſch
    -0.75
    POSITIVE LOGITS
    s
    1.02
     His
    0.61
    His
    0.56
    Their
    0.50
    whose
    0.50
     Whose
    0.49
     whose
    0.49
     HIS
    0.48
     s
    0.48
     Their
    0.47
    Activations Density 0.146%

    No Known Activations