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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120316
    Prev
    Next
    INDEX
    Explanations

    key terms related to political regions and entities, particularly involving conflict and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.65
     invokingState
    -0.61
     <=",
    -0.55
     CreateTagHelper
    -0.53
     []:
    -0.52
    VersionUID
    -0.50
    }>;
    -0.50
    AnimationsModule
    -0.49
     AssemblyCulture
    -0.48
     ModelRenderer
    -0.47
    POSITIVE LOGITS
    rafat
    0.68
     Palestinian
    0.57
    Palestinian
    0.56
     Palestinians
    0.50
     Palestina
    0.48
    Pfalz
    0.47
     Hamas
    0.46
     PopupWindow
    0.46
     الفلسطينية
    0.45
    EFIAPI
    0.41
    Activations Density 0.003%

    No Known Activations