Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 7478
    Prev
    Next
    INDEX
    Explanations

    references to characters involved in relationships or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     istrinya
    -0.69
     mouseY
    -0.67
    gehalt
    -0.60
    ädie
    -0.59
     Italijanski
    -0.59
    rolid
    -0.59
    EDEFAULT
    -0.57
    SerializedName
    -0.56
    viembre
    -0.56
     podjela
    -0.56
    POSITIVE LOGITS
    ")));
    
    0.67
    ExtendWith
    0.57
    "))
    
    0.53
     lenker
    0.52
    Hozzáférés
    0.51
    "/>
    
    0.51
    '));
    
    0.51
    __":
    
    0.51
    iecie
    0.50
    )));
    
    0.50
    Activations Density 3.245%

    No Known Activations