© 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. 1-GEMMASCOPE-RES-16K
    11. 10743
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tried" and related forms indicating attempts or testing

    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
    ništ
    -0.71
     located
    -0.66
    located
    -0.62
    Located
    -0.60
    NewGuid
    -0.58
    +#+#
    -0.58
    帖最后由
    -0.55
    Datuak
    -0.54
    tsburgh
    -0.54
    Identyfik
    -0.53
    POSITIVE LOGITS
    tried
    1.77
     tried
    1.74
     Tried
    1.53
     tested
    1.46
    Tried
    1.41
    tested
    1.33
     Tested
    1.31
    Tested
    1.25
     proven
    0.97
     experimented
    0.96
    Activations Density 0.086%

    No Known Activations