© 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. 7-GEMMASCOPE-RES-16K
    11. 12096
    Prev
    Next
    INDEX
    Explanations

    references to biological entities and structures related to scientific contexts

    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
    }))
    -0.81
    ılıyor
    -0.80
     مرئيه
    -0.76
     Morty
    -0.73
     Mukherjee
    -0.72
    fruta
    -0.70
    ilesh
    -0.70
    })));
    -0.69
     pinulongan
    -0.68
    }));
    -0.67
    POSITIVE LOGITS
     EAP
    0.86
     MainAxisSize
    0.84
     PAH
    0.82
     Vau
    0.81
     HasFactory
    0.80
     Cæsar
    0.80
     GAP
    0.80
     IMAP
    0.80
    AccessFile
    0.80
    pacman
    0.79
    Activations Density 4.356%

    No Known Activations