© 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. 7662
    Prev
    Next
    INDEX
    Explanations

    file system and directory-related error messages

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

    Code or file paths containing "root"

    np_acts-logits-general · gemini-2.0-flash

    /root/ directory paths

    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
    RR
    -0.48
    RSM
    -0.45
     UR
    -0.45
     RI
    -0.45
    ävän
    -0.44
    RPD
    -0.44
     RAS
    -0.43
    uris
    -0.43
    huri
    -0.43
     RR
    -0.42
    POSITIVE LOGITS
     root
    1.28
    root
    1.21
     region
    1.14
     rate
    1.07
     road
    1.05
    region
    1.02
     room
    0.99
     route
    0.98
     role
    0.95
    route
    0.94
    Activations Density 0.253%

    No Known Activations