Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10501
    Prev
    Next
    INDEX
    Explanations

    conditional statements and assertions in programming code

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

    Inequality checks or error handling

    np_acts-logits-general · gemini-2.0-flash

    not equal or not null

    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
    ")==
    -0.80
     lacked
    -0.75
    Lack
    -0.75
     propOrder
    -0.74
    LabelTagHelper
    -0.71
     lacking
    -0.69
     insufficient
    -0.69
     lacks
    -0.68
     dearth
    -0.68
     Lack
    -0.67
    POSITIVE LOGITS
     !=
    1.10
     nonzero
    0.99
     ≠
    0.89
    !=
    0.89
     !==
    0.83
    neq
    0.81
    assertNotNull
    0.80
     non
    0.79
    NotEmpty
    0.78
    ]!=
    0.77
    Activations Density 0.257%

    No Known Activations