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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3842
    Prev
    Next
    INDEX
    Explanations

    references to mercy and capital punishment

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

    Followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    legal and academic texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     especialmente
    -0.46
     extrêmement
    -0.43
     extremamente
    -0.42
     especially
    -0.42
     extremadamente
    -0.42
     totalité
    -0.41
     specifically
    -0.39
    tamment
    -0.39
     zowel
    -0.39
     speziell
    -0.38
    POSITIVE LOGITS
     doInBackground
    0.51
    __':
    0.50
    SPATH
    0.50
     MainAxisSize
    0.50
    ResponseWriter
    0.48
     nonUne
    0.48
    msgTypes
    0.47
     dilemmas
    0.47
    addContainerGap
    0.46
    __':
    0.46
    Activations Density 0.174%

    No Known Activations