© 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. 8442
    Prev
    Next
    INDEX
    Explanations

    expressions of emotion and sentiment related to honor and appreciation

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

    after quotations

    np_acts-logits-general · gemini-2.0-flash

    achieve dreams

    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
     CanadaChoose
    -0.53
    __":
    -0.49
     cherchés
    -0.49
    ništvo
    -0.47
     BoxFit
    -0.46
    
    -0.46
    twimg
    -0.45
     PeEnEo
    -0.43
    әрмәләр
    -0.42
     Мексичка
    -0.42
    POSITIVE LOGITS
     dreamed
    0.73
     dreamt
    0.72
     dream
    0.71
     dreams
    0.66
     rêve
    0.65
    dream
    0.63
     dreaming
    0.63
     droom
    0.63
     sogno
    0.62
     sogni
    0.62
    Activations Density 0.213%

    No Known Activations