© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 7041
    Prev
    Next
    INDEX
    Explanations

    words associated with character names and attributes in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.87
     poffible
    -0.72
     ſtand
    -0.72
     acorns
    -0.71
     Theſe
    -0.71
     Shakspeare
    -0.70
     canst
    -0.70
     Cæsar
    -0.70
     anhänger
    -0.70
    出版年
    -0.69
    POSITIVE LOGITS
     "
    0.77
     “
    0.77
     p
    0.64
     b
    0.64
     g
    0.62
    onAttach
    0.59
    CROSSTALK
    0.57
     m
    0.55
     ‘
    0.53
      
    0.53
    Activations Density 0.532%

    No Known Activations