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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 6180
    Prev
    Next
    INDEX
    Explanations

    references to birth and early life events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AFX
    -0.67
     themſelves
    -0.65
     autorytatywna
    -0.65
     wikihow
    -0.63
    RTDA
    -0.63
     Wikimedijinoj
    -0.62
     ſtand
    -0.61
     незавершена
    -0.61
    CONSIN
    -0.61
     acrylique
    -0.61
    POSITIVE LOGITS
     '\\;'
    0.58
    Born
    0.51
     Born
    0.47
     born
    0.47
    CREAT
    0.46
    gesetzt
    0.46
     sumpay
    0.45
    ]")]
    0.45
    extAlignment
    0.44
     ]];
    0.44
    Activations Density 0.037%

    No Known Activations