© 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. 4233
    Prev
    Next
    INDEX
    Explanations

    phrases that express recommendations, warnings, or considerations

    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
    UnsafeEnabled
    -0.49
    SequentialGroup
    -0.48
     autorytatywna
    -0.46
     @"/
    -0.40
    OGND
    -0.40
    المناصب
    -0.38
    ArgsConstructor
    -0.35
    auder
    -0.34
     للمعارف
    -0.34
    PYX
    -0.34
    POSITIVE LOGITS
     remember
    1.84
     bear
    1.78
     Remember
    1.53
    remember
    1.52
     note
    1.49
     keep
    1.49
    Remember
    1.48
     Bear
    1.46
    Bear
    1.46
    bear
    1.44
    Activations Density 0.458%

    No Known Activations