© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4265
    Prev
    Next
    INDEX
    Explanations

    significant code constructs or structures, particularly involving block delimiters and control flow statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.81
    ðsíða
    -0.81
     ſei
    -0.77
     """
    -0.76
     ſont
    -0.76
     ſondern
    -0.75
     ſeine
    -0.75
     []).
    -0.73
     ſehen
    -0.72
     ſeinen
    -0.72
    POSITIVE LOGITS
    }
    0.62
    if
    0.38
    PerformLayout
    0.38
    )
    0.34
    //
    0.31
    }
    0.29
     tantas
    0.28
     Investigaciones
    0.28
    return
    0.26
     redacción
    0.26
    Activations Density 0.064%

    No Known Activations