© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 4934
    Prev
    Next
    INDEX
    Explanations

    comments or concerns about privacy and surveillance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PERATURE
    -0.51
    PERTIES
    -0.50
     Various
    -0.49
    ]>=
    -0.49
    muffin
    -0.48
    riwal
    -0.46
    IBAction
    -0.46
    İstinadlar
    -0.46
    various
    -0.45
    IALES
    -0.45
    POSITIVE LOGITS
    تقاوى
    1.01
     definitely
    0.81
    ंदीखरीदारी
    0.81
     absolutely
    0.76
    <em>
    0.72
    expandindo
    0.70
     really
    0.70
     todella
    0.66
    DockStyle
    0.66
    Personendaten
    0.65
    Activations Density 0.193%

    No Known Activations