© 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. 22-GEMMASCOPE-RES-16K
    11. 14628
    Prev
    Next
    INDEX
    Explanations

    instances of control and letting go in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtill
    -0.47
     purpoſe
    -0.47
    PMailer
    -0.47
     wireType
    -0.44
     AssemblyCompany
    -0.43
     hiding
    -0.43
     fizer
    -0.43
     ſta
    -0.42
    ceğini
    -0.42
    windowFixed
    -0.41
    POSITIVE LOGITS
     allowed
    0.59
     Allow
    0.55
     let
    0.53
     Allowed
    0.53
     allow
    0.53
     letting
    0.52
     lets
    0.52
     allows
    0.51
     Allows
    0.51
    slide
    0.49
    Activations Density 0.216%

    No Known Activations