© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 15436
    Prev
    Next
    INDEX
    Explanations

    Java class inheritance and implementation relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.83
     SQLAlchemy
    -0.67
    SequentialGroup
    -0.65
     BoxDecoration
    -0.64
    oneofs
    -0.60
     Kaly
    -0.60
    pulumi
    -0.60
    AutoresizingMask
    -0.59
    ophen
    -0.57
     membership
    -0.57
    POSITIVE LOGITS
     extends
    1.69
    extends
    1.61
     extiende
    0.84
    implements
    0.81
     extend
    0.77
     extending
    0.74
     implements
    0.73
     Extending
    0.65
     defaultstate
    0.64
    extend
    0.62
    Activations Density 0.057%

    No Known Activations