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. 8-GEMMASCOPE-RES-16K
    6. 5933
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons and statistical measurements in data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osan
    -0.51
     cortes
    -0.44
    nol
    -0.44
     Spring
    -0.44
    iece
    -0.43
    Spring
    -0.43
    romp
    -0.42
     subject
    -0.42
    وى
    -0.42
    odom
    -0.41
    POSITIVE LOGITS
    principalColumn
    0.85
     AspNetCore
    0.78
     OFDb
    0.77
    onAttach
    0.75
     мәкал
    0.74
     /\.(
    0.73
    +#+#
    0.73
     newOwner
    0.72
    __);
    0.72
     "..\..\..\
    0.72
    Activations Density 1.802%

    No Known Activations