© 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. 37-GEMMASCOPE-RES-16K
    6. 3468
    Prev
    Next
    INDEX
    Explanations

    mentions of "Lam", "lamb", and variations related to lamb or lamb-related festivals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Explicit
    -0.42
    TypedDataSet
    -0.38
     itſelf
    -0.37
     fhew
    -0.33
    FailureListener
    -0.32
     Direct
    -0.32
     betweenstory
    -0.32
    Direct
    -0.32
    cshtml
    -0.31
    目で
    -0.31
    POSITIVE LOGITS
    Lam
    0.69
     Lam
    0.68
     Lem
    0.64
    Tembelea
    0.60
    orghini
    0.58
    Lem
    0.56
    DockStyle
    0.54
    Lamp
    0.52
     لام
    0.52
     lem
    0.52
    Activations Density 0.311%

    No Known Activations