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. 13231
    Prev
    Next
    INDEX
    Explanations

    written instructions or guidelines related to specific processes or actions

    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
     المعيارى
    -1.02
    expandindo
    -0.92
    IntoConstraints
    -0.91
    webElementXpaths
    -0.82
    (&:
    -0.82
    ConstraintMaker
    -0.79
     beginnetje
    -0.79
    IUrlHelper
    -0.79
    Parcelize
    -0.78
     snippetHide
    -0.74
    POSITIVE LOGITS
    </em>
    0.50
     role
    0.48
    में
    0.47
    нъ
    0.46
    Gov
    0.44
     super
    0.43
    ोंने
    0.42
     M
    0.42
     r
    0.41
     hit
    0.41
    Activations Density 0.595%

    No Known Activations