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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11154
    Prev
    Next
    INDEX
    Explanations

    different types of tags or labels used in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UseVisualStyle
    -0.39
    
    -0.35
    cdnjs
    -0.33
     Goodrich
    -0.32
     czemu
    -0.32
    proken
    -0.31
    ("="
    -0.31
     maisha
    -0.31
    REDIRECT
    -0.30
    ENED
    -0.30
    POSITIVE LOGITS
     Tag
    0.79
     tag
    0.74
     tagName
    0.73
     tagging
    0.73
     TAG
    0.71
     tags
    0.71
    Tag
    0.68
     Tags
    0.66
    TagMode
    0.65
    tag
    0.64
    Activations Density 0.085%

    No Known Activations