© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3784
    Prev
    Next
    INDEX
    Explanations

    the presence of the "<bos>" token, indicating the start of a new section or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     increí
    -0.58
     againſt
    -0.50
    <unused20>
    -0.50
     pleaſure
    -0.50
    <unused93>
    -0.50
    "}")
    -0.50
     drey
    -0.50
    
    -0.49
     ſeyn
    -0.49
    <unused43>
    -0.49
    POSITIVE LOGITS
    toxicity
    1.82
     toxicity
    0.61
    toxic
    0.52
    Toxicity
    0.52
     Toxicity
    0.49
    staticmethod
    0.46
    xicity
    0.45
    typeDefinition
    0.43
    ViewFeatures
    0.43
     ***!
    0.42
    Activations Density 0.015%

    No Known Activations