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. 5-GEMMASCOPE-RES-16K
    6. 8873
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate the end or separation of sentences or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    []
    
    -0.76
    columnHeader
    -0.64
    
    -0.64
     ]
    
    -0.63
    &
    
    -0.62
    _
    
    -0.61
    terday
    -0.61
    =()=>{
    -0.61
     tslint
    -0.61
    ++
    
    -0.61
    POSITIVE LOGITS
    +#+#
    0.66
    )).
    0.65
     مشين
    0.65
     utafitiHapana
    0.64
    ))
    0.63
     Numerade
    0.63
    )),
    0.62
    ).
    0.62
    ])
    0.62
    ?).
    0.61
    Activations Density 0.276%

    No Known Activations