© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 9733
    Prev
    Next
    INDEX
    Explanations

    elements of code related to method or function declarations and invocations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.62
    __))
    -0.62
    ])
    
    -0.57
    )"),
    -0.54
    ])]
    -0.54
    "));
    
    -0.53
    ])));
    -0.52
    ]),
    
    -0.51
    )))
    
    -0.51
    _))
    -0.50
    POSITIVE LOGITS
    WireFormatLite
    0.80
    ThroughAttribute
    0.74
     متعلقه
    0.71
    исленность
    0.70
    Brainz
    0.69
    therly
    0.69
    bootstrapcdn
    0.65
    (&:
    0.65
    Rüyada
    0.65
    脚注の使い方
    0.64
    Activations Density 0.150%

    No Known Activations