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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11312
    Prev
    Next
    INDEX
    Explanations

    attributes and settings related to layout and visibility in UI components

    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
    rawDesc
    -0.54
    OrNil
    -0.43
    InjectAttribute
    -0.38
    HasAnnotation
    -0.37
    DockStyle
    -0.33
    SourceChecksum
    -0.32
     circle
    -0.32
     escor
    -0.31
    ','',
    -0.31
     Coul
    -0.31
    POSITIVE LOGITS
     purpoſe
    0.67
     leaſt
    0.65
     houſe
    0.62
     itſelf
    0.60
     pleaſure
    0.60
     ſche
    0.59
    RetentionPolicy
    0.58
     myſelf
    0.58
     ſte
    0.57
    ſelf
    0.57
    Activations Density 0.254%

    No Known Activations