Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5845
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a strong relationship or closeness between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nélk
    -0.58
    beeld
    -0.58
     elég
    -0.57
     plötzlich
    -0.56
     lenne
    -0.56
     néz
    -0.55
     Rhymes
    -0.51
     miglior
    -0.51
    ñoz
    -0.50
     kér
    -0.50
    POSITIVE LOGITS
     carefully
    1.34
     tightly
    1.22
     closely
    1.19
     firmly
    1.17
    caref
    1.16
     Carefully
    1.00
     cuidadosamente
    0.91
     gently
    0.88
    Portail
    0.85
     loosely
    0.84
    Activations Density 0.122%

    No Known Activations