© 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
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 2031
    Prev
    Next
    INDEX
    Explanations

    arguments related to the impact of harmful statements on others' well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.59
    SequentialGroup
    -0.49
     հղումներ
    -0.47
    ApiModel
    -0.44
    URLException
    -0.44
    queryInterface
    -0.42
    Autoritní
    -0.41
    WithMany
    -0.41
    ClientSize
    -0.40
    HtmlAttribute
    -0.40
    POSITIVE LOGITS
     uttered
    1.40
     words
    1.09
     spoken
    1.07
     utterance
    1.06
     uttering
    1.02
     phrasing
    0.98
     verbal
    0.97
     phrases
    0.95
     utterances
    0.93
    spoken
    0.91
    Activations Density 0.786%

    No Known Activations