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. 7-GEMMASCOPE-RES-16K
    6. 9464
    Prev
    Next
    INDEX
    Explanations

    markers of technical language and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.99
    fromnode
    -0.88
    ']").
    -0.88
     ويكيميديا
    -0.87
    }}},
    -0.83
    }?>
    -0.82
    ']],
    -0.82
    ']):
    -0.81
    Šaltiniai
    -0.81
    "]),
    -0.80
    POSITIVE LOGITS
    itemize
    0.72
     truss
    0.66
     tourmaline
    0.64
     sows
    0.64
     Machu
    0.61
     tsar
    0.60
     oars
    0.60
     defaultstate
    0.59
     loch
    0.59
    nonatomic
    0.58
    Activations Density 0.016%

    No Known Activations