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. 2-GEMMASCOPE-RES-16K
    6. 3818
    Prev
    Next
    INDEX
    Explanations

    words related to admissions and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]]
    
    -0.73
    "]]
    -0.68
    ))
    
    -0.67
    }}
    
    -0.62
     "]";
    -0.61
    )]
    
    -0.59
    bolista
    -0.58
    )));
    -0.58
    ):(
    -0.58
    ')"
    -0.57
    POSITIVE LOGITS
     Efq
    0.97
     purpoſe
    0.88
     cauſe
    0.78
     greateſt
    0.75
     perſon
    0.74
     Majefty
    0.74
     reaſon
    0.71
    γων
    0.71
     fubject
    0.71
     ſche
    0.71
    Activations Density 0.052%

    No Known Activations