© 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. 3524
    Prev
    Next
    INDEX
    Explanations

    commands and operations related to SSH key management and permissions

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

    File permissions and modes

    np_acts-logits-general · gemini-2.0-flash

    file permissions and modes

    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
     doInBackground
    -0.68
    MigrationBuilder
    -0.66
    BackPressed
    -0.65
    ásban
    -0.64
     ivelany
    -0.59
     Remastered
    -0.58
    TAKT
    -0.57
     transfieras
    -0.56
    quial
    -0.55
    artner
    -0.54
    POSITIVE LOGITS
     permissions
    0.64
    permissions
    0.61
     mode
    0.60
     modes
    0.59
    Permissions
    0.58
     sy
    0.57
     owner
    0.56
     ownership
    0.56
     Permissions
    0.55
    transQ
    0.55
    Activations Density 0.507%

    No Known Activations