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. 15-GEMMASCOPE-RES-16K
    6. 2720
    Prev
    Next
    INDEX
    Explanations

    references to scientific methodologies and experimental procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.91
     esternos
    -0.87
     שוליים
    -0.82
     propOrder
    -0.78
     joaat
    -0.77
    ագրություններ
    -0.76
    __":
    
    -0.76
     للاسماء
    -0.72
    WebControls
    -0.72
    rungsseite
    -0.70
    POSITIVE LOGITS
    ).
    0.79
    }.
    0.69
    .)
    0.68
    }$.\\
    0.67
     and
    0.63
    ailleurs
    0.62
    )。
    0.61
    .).
    0.61
    .”
    0.61
    ].
    0.61
    Activations Density 0.832%

    No Known Activations