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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4105
    Prev
    Next
    INDEX
    Explanations

    specific legal and medical terms related to processes and outcomes

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

    following "after" or similar words

    np_acts-logits-general · gemini-2.0-flash

    post- words and afterwards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.51
    ParallelGroup
    -0.45
    تقاوى
    -0.44
     ModelExpression
    -0.42
    }$​
    -0.38
    complexType
    -0.38
    ":[{
    -0.38
    voke
    -0.37
     Variation
    -0.36
    }})
    -0.36
    POSITIVE LOGITS
    Afterwards
    0.73
     Afterwards
    0.70
     afterwards
    0.69
     afterward
    0.67
     Afterward
    0.60
     danach
    0.57
    #+#
    0.56
     Danach
    0.56
    UnsafeEnabled
    0.56
     Posteriormente
    0.54
    Activations Density 0.428%

    No Known Activations