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. 11-GEMMASCOPE-RES-16K
    6. 1914
    Prev
    Next
    INDEX
    Explanations

    references to mathematical symbols and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    and
    -0.62
    me
    -0.58
    is
    -0.57
     ALL
    -0.57
     kids
    -0.56
     FREE
    -0.56
    ar
    -0.55
    one
    -0.55
     waters
    -0.55
     Gerr
    -0.55
    POSITIVE LOGITS
    setVerticalGroup
    1.21
     insuffisamment
    0.99
     AssemblyCulture
    0.93
    findpost
    0.92
    didSet
    0.89
    ".
    
    0.88
    ])));
    0.85
     familières
    0.82
    ")));
    
    0.82
    })).
    0.81
    Activations Density 1.448%

    No Known Activations