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. 7-GEMMASCOPE-RES-16K
    6. 9545
    Prev
    Next
    INDEX
    Explanations

    specific references to URLs or paths in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppColors
    -0.74
     Theſe
    -0.67
     cdti
    -0.67
     mourut
    -0.65
     SafeMath
    -0.64
    orem
    -0.64
     Cæsar
    -0.62
     uchiha
    -0.62
    قایناقلار
    -0.61
     poffible
    -0.61
    POSITIVE LOGITS
    DebuggerNonUser
    1.08
     '{@
    0.97
    ("")]
    0.91
    MigrationBuilder
    0.86
    migrationBuilder
    0.84
    localctx
    0.78
    tagHelperRunner
    0.77
    MemoryWarning
    0.76
    تقاوى
    0.73
    templateUrl
    0.69
    Activations Density 0.005%

    No Known Activations