Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 1550
    Prev
    Next
    INDEX
    Explanations

    terms related to connectivity and integration in technology

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

    Followed by "any"

    np_acts-logits-general · gemini-2.0-flash

    any, anything, anywhere

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ]=>
    -0.64
     للمعارف
    -0.63
     समीक्षाएं
    -0.63
     للاسماء
    -0.61
    IBOutlet
    -0.58
     صوتيه
    -0.57
     })}
    -0.55
    Билгалдахарш
    -0.55
    OGND
    -0.54
     <=",
    -0.53
    POSITIVE LOGITS
     any
    3.21
    Any
    2.83
    any
    2.75
     ANY
    2.73
     Any
    2.72
     cualquier
    2.63
     qualquer
    2.60
     anything
    2.59
     anyone
    2.58
    ANY
    2.50
    Activations Density 0.961%

    No Known Activations