© 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. 22-GEMMASCOPE-RES-16K
    11. 5741
    Prev
    Next
    INDEX
    Explanations

    concepts related to assumptions and conditions in theoretical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "is" or similar verb

    np_acts-logits-general · gemini-2.0-flash

    is descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
     <=",
    -0.55
    ChildScrollView
    -0.53
    ValueGenerated
    -0.49
    ThroughAttribute
    -0.48
     dAtA
    -0.47
    msgTypes
    -0.47
    gouv
    -0.47
     DBNull
    -0.47
     feltro
    -0.46
     Absol
    -0.46
    POSITIVE LOGITS
    =$?
    0.67
     motivates
    0.66
     motivate
    0.62
     naturel
    0.61
     motivated
    0.61
     Lleva
    0.60
     nai
    0.59
     tempting
    0.58
    motivated
    0.58
    atural
    0.57
    Activations Density 2.010%

    No Known Activations