© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9015
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and concepts related to estimators and adjustments in statistical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     best
    -0.40
     r
    -0.40
    頃に
    -0.40
    頃の
    -0.38
     mich
    -0.37
     beste
    -0.37
     منها
    -0.36
     she
    -0.36
     che
    -0.36
    在她
    -0.35
    POSITIVE LOGITS
    GEBURTSDATUM
    1.15
    
    0.99
     purpoſe
    0.95
    tagHelperRunner
    0.95
    ChildScrollView
    0.93
    extAlignment
    0.91
     houſe
    0.89
    ]--;
    0.89
     مشين
    0.87
     myſelf
    0.86
    Activations Density 1.700%

    No Known Activations