© 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. 3817
    Prev
    Next
    INDEX
    Explanations

    phrases expressing dissatisfaction or challenges related to experiences and systems

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

    Sentences containing "while" or "although"

    np_acts-logits-general · gemini-2.0-flash

    although / though / while

    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
    RectangleBorder
    -0.65
    principalColumn
    -0.64
     InputDecoration
    -0.63
    tagHelperRunner
    -0.62
    bcryptjs
    -0.60
    httphttps
    -0.60
    WebServlet
    -0.59
    multirow
    -0.58
    majánló
    -0.58
     otomatig
    -0.57
    POSITIVE LOGITS
     still
    0.62
     nonetheless
    0.54
    still
    0.54
     overall
    0.49
    畢竟
    0.49
    Still
    0.48
     ultimately
    0.47
     Still
    0.47
     nevertheless
    0.47
    それでも
    0.46
    Activations Density 0.257%

    No Known Activations