Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15672
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer service and feedback

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

    Text requesting or suggesting an action

    np_acts-logits-general · gemini-2.0-flash

    requests and pleas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.44
     Pingback
    -0.37
    arXiv
    -0.34
     vVar
    -0.31
     mine
    -0.30
    artig
    -0.30
     segue
    -0.29
    ないけど
    -0.28
    DockStyle
    -0.28
     pal
    -0.27
    POSITIVE LOGITS
     please
    2.89
    please
    2.47
     Please
    2.45
    Please
    2.42
     PLEASE
    2.16
    请
    1.91
    PLEASE
    1.91
     plz
    1.90
     pls
    1.86
     bitte
    1.84
    Activations Density 0.264%

    No Known Activations