© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4015
    Prev
    Next
    INDEX
    Explanations

    instances of the word "however" in various forms

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

    "However" at the beginning of a sentence

    np_acts-logits-general · gemini-2.0-flash

    introducing contrast

    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
     oprot
    -0.60
    ScopeManager
    -0.59
     sumpay
    -0.57
     BoxFit
    -0.54
     متعلقه
    -0.54
     iNdEx
    -0.53
     fieldNum
    -0.53
     estekak
    -0.52
    WriteBarrier
    -0.51
     Beet
    -0.50
    POSITIVE LOGITS
     demikian
    0.60
    że
    0.49
     مشين
    0.48
     avoient
    0.47
     senhora
    0.47
     Bucure
    0.45
    toarele
    0.45
    atorul
    0.45
     enví
    0.44
     слід
    0.44
    Activations Density 0.088%

    No Known Activations