© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13373
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or physical protections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    DeleteBehavior
    -0.50
    yarnpkg
    -0.44
    SequentialGroup
    -0.43
     MainAxisSize
    -0.40
    kwür
    -0.39
    ✭✭
    -0.38
    ypos
    -0.38
     casó
    -0.37
    AndView
    -0.36
     meub
    -0.36
    POSITIVE LOGITS
     protection
    3.55
     protect
    3.28
     Protection
    3.20
    protection
    3.19
     protecting
    3.14
    Protection
    3.09
    protect
    3.03
     Protect
    3.03
     protective
    3.00
     PROTECTION
    2.98
    Activations Density 0.157%

    No Known Activations