© 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. 1-GEMMASCOPE-RES-16K
    11. 10823
    Prev
    Next
    INDEX
    Explanations

    terms related to direct causation or direct effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compliant
    -0.67
    ValueStyle
    -0.66
    scaler
    -0.61
     nahilalakip
    -0.60
    /]
    -0.60
    survi
    -0.59
     Umbra
    -0.58
    mhz
    -0.57
    ImageContext
    -0.57
    istiwa
    -0.57
    POSITIVE LOGITS
     direct
    2.11
     Direct
    1.90
    direct
    1.84
    Direct
    1.73
    DIRECT
    1.43
     DIRECT
    1.38
     indirect
    1.25
     directo
    1.25
     direkte
    1.22
     direkten
    1.21
    Activations Density 0.066%

    No Known Activations