© 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. 5617
    Prev
    Next
    INDEX
    Explanations

    references to field and property attributes in code contexts

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

    Lua code referencing game modes or card suits

    np_acts-logits-general · gemini-2.0-flash

    checking variable equality

    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
     tot
    -0.46
    esistenza
    -0.43
    \{\\
    -0.41
    Poco
    -0.41
    however
    -0.40
    uckle
    -0.40
     haar
    -0.40
    nodoc
    -0.40
    lenburg
    -0.39
    にとって
    -0.39
    POSITIVE LOGITS
     ==
    1.39
     ===
    1.25
    ==
    0.91
     isEqualToString
    0.90
     !=
    0.82
     !==
    0.82
    CppMethod
    0.82
    ==$
    0.81
    ===
    0.79
    ']==
    0.73
    Activations Density 0.224%

    No Known Activations