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. 41-GEMMASCOPE-RES-16K
    6. 7118
    Prev
    Next
    INDEX
    Explanations

    indices or identifiers of elements within a structured context, such as coding or technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ),
    
    -0.73
    )、
    -0.72
    ,”
    -0.71
    )،
    -0.71
     )
    -0.70
    "،
    -0.69
    ”،
    -0.69
    )、
    -0.67
    :
    -0.66
     。
    -0.65
    POSITIVE LOGITS
     ,
    1.07
     transfieras
    0.61
     <<<<<<<<<<<<<<
    0.54
     الرياضيه
    0.52
     AssemblyCompany
    0.52
     estekak
    0.50
    Билгалдахарш
    0.49
    كويكب
    0.48
    twimg
    0.47
    évaluateur
    0.47
    Activations Density 0.127%

    No Known Activations