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. 11-GEMMASCOPE-RES-16K
    6. 6232
    Prev
    Next
    INDEX
    Explanations

    configuration parameters and potential changes in code

    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
    DoubleQuotes
    -0.59
     Créez
    -0.55
    ItemBackground
    -0.54
    alnız
    -0.54
    ]=>
    -0.49
    focusable
    -0.49
     belie
    -0.48
    ITAN
    -0.47
    瘍
    -0.47
    硃
    -0.46
    POSITIVE LOGITS
    <sup>
    0.87
     propOrder
    0.83
     surla
    0.82
    原始内容存档于
    0.78
    脚注の使い方
    0.76
    enumii
    0.72
     defaultstate
    0.70
    MemoryWarning
    0.67
    WaitGroup
    0.67
    VersionUID
    0.66
    Activations Density 0.039%

    No Known Activations