© 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. 4576
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries related to determination and investigation

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

    preceding an inquiry or investigation

    np_acts-logits-general · gemini-2.0-flash

    inquire whether

    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
    hoeddwyd
    -0.46
    MergeFrom
    -0.42
     stok
    -0.40
    tagHelperRunner
    -0.40
     kom
    -0.39
    OuterAlt
    -0.37
     ويكيپيديا
    -0.36
     varsity
    -0.35
     postcard
    -0.35
     sk
    -0.34
    POSITIVE LOGITS
     whether
    2.41
    whether
    2.09
     Whether
    1.87
    Whether
    1.83
     WHETHER
    1.72
     apakah
    1.67
    是否
    1.50
     آیا
    1.45
     是否
    1.27
    是否有
    1.27
    Activations Density 0.810%

    No Known Activations