© 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. 3613
    Prev
    Next
    INDEX
    Explanations

    the prefix "fo" indicating a possible focus on derivatives or variations of specific root words

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

    Following "Fo" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    fo words

    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
    cotch
    -0.59
    setContentView
    -0.52
    OrCreate
    -0.51
    ```
    -0.48
     createState
    -0.46
    <table>
    -0.45
     observa
    -0.45
    <h6>
    -0.45
    ogi
    -0.44
    abetes
    -0.44
    POSITIVE LOGITS
     Roskov
    0.82
     Fo
    0.81
    Fo
    0.68
     يتيمه
    0.67
    __':
    0.66
     pleaſure
    0.66
     CreateTagHelper
    0.64
     FO
    0.64
     Mox
    0.63
     itſelf
    0.62
    Activations Density 0.137%

    No Known Activations