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. 14-GEMMASCOPE-RES-16K
    6. 26
    Prev
    Next
    INDEX
    Explanations

    references to boys and girls, particularly in contexts related to youth activities or narratives

    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
     للمعارف
    -0.81
    Composable
    -0.81
    >")
    -0.81
     الحره
    -0.79
     InputDecoration
    -0.77
    }],
    
    -0.76
    "=>"
    -0.75
    \}}
    -0.72
     >::
    -0.72
     "").
    -0.72
    POSITIVE LOGITS
     boys
    1.42
     Boys
    1.41
     BOYS
    1.35
    Boys
    1.33
    Boy
    1.32
     boy
    1.29
     BOY
    1.25
    boy
    1.25
    boys
    1.23
     Boy
    1.19
    Activations Density 0.040%

    No Known Activations