© 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. 11303
    Prev
    Next
    INDEX
    Explanations

    API endpoints and related URL structures in code snippets

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

    Code-related URL paths

    np_acts-logits-general · gemini-2.0-flash

    paths/endpoints/api references

    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
     The
    -0.43
    ítulo
    -0.43
     Brown
    -0.42
    FormTagHelper
    -0.41
    外部リンク
    -0.41
     menyer
    -0.40
    WANTED
    -0.39
    NegativeButton
    -0.39
     Dam
    -0.39
     Mad
    -0.39
    POSITIVE LOGITS
    api
    1.00
    #!/
    0.74
    Personendaten
    0.73
    
    0.73
     api
    0.73
     endwhile
    0.71
    findpost
    0.71
    الإنجليزية
    0.70
    #
    0.69
    ?")
    0.68
    Activations Density 0.103%

    No Known Activations