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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 3984
    Prev
    Next
    INDEX
    Explanations

    words related to dog training and behavior management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.53
     يتيمه
    -0.50
    rrggbb
    -0.48
    ByVersion
    -0.46
    TypedDataSet
    -0.44
    Ārējās
    -0.42
    ChildScrollView
    -0.41
    LEncoder
    -0.40
    省市镇
    -0.40
     kasarigan
    -0.40
    POSITIVE LOGITS
     dog
    2.92
     dogs
    2.83
     Dogs
    2.48
     Dog
    2.45
    Dog
    2.39
    Dogs
    2.38
    dog
    2.34
     canine
    2.25
    dogs
    2.25
     DOG
    2.20
    Activations Density 0.324%

    No Known Activations