© 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. 17-GEMMASCOPE-RES-16K
    6. 806
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives related to products, emphasizing their features and qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    😦
    -0.62
    ногда
    -0.58
     (“
    -0.58
     “
    -0.54
     («
    -0.54
    waite
    -0.53
    というか
    -0.51
     Sometime
    -0.51
     strangest
    -0.50
    ölk
    -0.49
    POSITIVE LOGITS
     WaitForSeconds
    0.68
    durable
    0.66
     ComVisible
    0.66
     durable
    0.65
     oprot
    0.65
     للاسماء
    0.65
    shutil
    0.61
     chi̍t
    0.58
     StatelessWidget
    0.58
     youll
    0.58
    Activations Density 0.091%

    No Known Activations