© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10352
    Prev
    Next
    INDEX
    Explanations

    conditional statements and their associated consequences

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

    Noun followed by "is" or describing system/project failure

    np_acts-logits-general · gemini-2.0-flash

    failure or problem states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     probably
    -0.92
    probably
    -0.87
     Probably
    -0.85
    Probably
    -0.85
    ngdoc
    -0.76
     prolly
    -0.74
     sicherlich
    -0.71
     doubtless
    -0.67
    certainly
    -0.67
     wohl
    -0.67
    POSITIVE LOGITS
     fails
    1.04
     exceeds
    0.88
     happens
    0.87
     weren
    0.84
     fail
    0.80
     ever
    0.77
     proves
    0.75
     вдруг
    0.74
    有任何
    0.74
     happen
    0.73
    Activations Density 0.532%

    No Known Activations