© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 838
    Prev
    Next
    INDEX
    Explanations

    elements related to programming functions and their attributes

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

    Keywords followed by an exclamation point

    np_acts-logits-general · gemini-2.0-flash

    null checks and error handling

    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
    Portale
    -0.67
     approval
    -0.64
     approved
    -0.59
    >*/
    -0.54
     approve
    -0.54
     approving
    -0.53
     Society
    -0.53
     Recep
    -0.52
    approved
    -0.52
     approves
    -0.51
    POSITIVE LOGITS
     NULL
    0.74
    assertNull
    0.74
    Nullable
    0.73
     nil
    0.73
     None
    0.67
    EDEFAULT
    0.65
     nullptr
    0.64
     nullable
    0.62
     absent
    0.61
    NULL
    0.60
    Activations Density 0.176%

    No Known Activations