© 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. 2-GEMMASCOPE-RES-16K
    6. 8170
    Prev
    Next
    INDEX
    Explanations

    instances of the word "share" in various contexts

    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
    PyExc
    -0.66
    ContentAsync
    -0.66
    /*---
    -0.63
     magát
    -0.59
     indisponible
    -0.59
    EndInit
    -0.58
    ioutil
    -0.57
    fxml
    -0.57
    зино
    -0.57
    horabuena
    -0.56
    POSITIVE LOGITS
     share
    3.67
    share
    3.31
     Share
    3.24
     shares
    3.19
     sharing
    3.19
     SHARE
    3.10
    Share
    3.05
     Sharing
    2.93
    sharing
    2.86
     shared
    2.84
    Activations Density 0.068%

    No Known Activations