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. 2-GEMMASCOPE-RES-16K
    6. 3760
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "str" and related variations indicating string manipulation or representation

    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
    تفصیلات
    -0.71
     Broadcast
    -0.71
     leaſt
    -0.60
    Broadcast
    -0.59
    strings
    -0.57
     unknowns
    -0.54
     broadcast
    -0.54
     myſelf
    -0.54
     wrists
    -0.54
    crimin
    -0.53
    POSITIVE LOGITS
    fromnode
    0.93
     str
    0.85
    ViewFeatures
    0.74
    ::::::::
    0.73
    gnore
    0.72
    psum
    0.71
    Diweddarwch
    0.70
    mybatisplus
    0.68
    ymce
    0.68
    actionMode
    0.66
    Activations Density 0.061%

    No Known Activations