© 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. 805
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives that emphasize opinions or feelings about topics

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

    "a" followed by a negative word

    np_acts-logits-general · gemini-2.0-flash

    it's a [situation descriptor]

    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
     ulteriori
    -0.53
     rekke
    -0.49
     '\\;'
    -0.47
     recours
    -0.47
    mybatisplus
    -0.45
     yore
    -0.43
     Ruhm
    -0.43
     paio
    -0.42
     lccn
    -0.41
    yet
    -0.41
    POSITIVE LOGITS
     joke
    0.84
     matter
    0.81
    حوالہ
    0.75
     problem
    0.74
     question
    0.73
    SequentialGroup
    0.71
     pity
    0.70
     bad
    0.70
     gamble
    0.70
     uphill
    0.69
    Activations Density 0.291%

    No Known Activations