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. 24-GEMMASCOPE-RES-16K
    6. 12705
    Prev
    Next
    INDEX
    Explanations

    terms related to abandonment or leaving behind

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

    the word "leave" or "left."

    np_acts-logits-general · gemini-2.0-flash

    leave them behind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.72
    الإنجليزية
    -0.60
    (@"%@",
    -0.59
    setVerticalGroup
    -0.59
    StartTag
    -0.54
    webElementXpaths
    -0.52
     ulang
    -0.51
    tagHelperRunner
    -0.50
    #
    -0.50
     kịch
    -0.50
    POSITIVE LOGITS
     behind
    1.39
    behind
    1.16
     Behind
    0.97
    Behind
    0.97
     BEHIND
    0.95
     trás
    0.91
     atrás
    0.88
     derrière
    0.84
     traces
    0.83
     room
    0.82
    Activations Density 0.093%

    No Known Activations