© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 7802
    Prev
    Next
    INDEX
    Explanations

    events related to press conferences and public gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     novedad
    -0.52
    TargetException
    -0.52
    }))
    -0.52
    
    -0.50
     cố
    -0.49
    SerializedSize
    -0.49
    dictions
    -0.48
    mele
    -0.48
     isInitialized
    -0.48
    ])):
    -0.47
    POSITIVE LOGITS
     press
    1.03
     presse
    0.84
     panel
    0.80
    press
    0.78
     Presse
    0.76
     reception
    0.72
    presse
    0.71
     gala
    0.70
     awards
    0.70
     launch
    0.68
    Activations Density 0.261%

    No Known Activations