© 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. 5636
    Prev
    Next
    INDEX
    Explanations

    conditional statements and user instructions related to error handling and issue resolution

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

    Action performed by the user

    np_acts-logits-general · gemini-2.0-flash

    actions like try, open, select

    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
    FormTagHelper
    -0.49
     defStyleAttr
    -0.46
    std
    -0.46
     Ici
    -0.45
    fml
    -0.45
    angliski
    -0.45
     AssemblyVersion
    -0.44
     lavadora
    -0.44
    Facades
    -0.43
     téléphonique
    -0.43
    POSITIVE LOGITS
     open
    0.77
     copy
    0.74
     disambiguazione
    0.73
     double
    0.64
     edit
    0.63
     navigate
    0.63
     MenuView
    0.62
     opened
    0.61
     navig
    0.61
    lauch
    0.61
    Activations Density 0.444%

    No Known Activations