© 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. 4383
    Prev
    Next
    INDEX
    Explanations

    terms related to agreements in media and broadcasting contexts

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

    Followed by "usually" or similar adverbs

    np_acts-logits-general · gemini-2.0-flash

    usually associated with relationships or states

    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
     nawr
    -0.47
     betweenstory
    -0.44
    providedIn
    -0.41
    췄
    -0.41
    "}";
    -0.40
     الحره
    -0.38
     الحالي
    -0.36
    ...";
    -0.35
    {}\
    -0.34
    
    -0.34
    POSITIVE LOGITS
     usually
    2.25
     typically
    2.06
    usually
    1.93
     Usually
    1.90
    Usually
    1.89
     often
    1.84
     biasanya
    1.79
    Typically
    1.77
     Typically
    1.77
    typically
    1.77
    Activations Density 1.321%

    No Known Activations