© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 713
    Prev
    Next
    INDEX
    Explanations

    PHP method calls, particularly in object-oriented programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    reference to method calls and assertions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    further offences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     connues
    -0.53
     amac
    -0.49
    SystemColors
    -0.49
    つか
    -0.47
    slidesToShow
    -0.47
    océan
    -0.47
     attirer
    -0.46
    tvrt
    -0.46
    讓我們
    -0.46
     romantique
    -0.45
    POSITIVE LOGITS
    WithIOException
    0.81
    #
    0.80
    Према
    0.76
    #+#
    0.75
    mockMvc
    0.74
    })->
    0.73
    :+:
    0.72
    ViewFeatures
    0.71
    sizeCache
    0.71
     >=",
    0.70
    Activations Density 0.012%

    No Known Activations