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. 10-GEMMASCOPE-RES-16K
    6. 10783
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stat
    -0.53
    prima
    -0.53
    mara
    -0.49
     St
    -0.48
    <eos>
    -0.48
    新娘
    -0.48
     market
    -0.47
     Keyes
    -0.47
    Ring
    -0.46
    Prima
    -0.46
    POSITIVE LOGITS
    |}
    1.33
    ||}
    1.18
    }")]
    1.17
    ConstraintMaker
    1.10
     }}$}
    1.03
    UnusedPrivate
    0.93
    !")
    
    0.91
    RenderAtEndOf
    0.90
    |}\
    0.89
     CreateTagHelper
    0.89
    Activations Density 0.008%

    No Known Activations