© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4746
    Prev
    Next
    INDEX
    Explanations

    closing brackets and commas in structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?)
    -0.58
     transfieras
    -0.55
    )
    -0.55
    ??)
    -0.53
    ())
    -0.52
    makedirs
    -0.52
    ================
    -0.50
     ControllerBase
    -0.50
    PHEN
    -0.49
    ⓧ
    -0.49
    POSITIVE LOGITS
    },
    1.86
     },
    1.68
    },
    1.54
    '},
    1.33
    "},
    1.28
    .},
    1.10
    ()},
    1.09
    ]},
    1.07
     },
    1.05
    }.
    0.96
    Activations Density 0.264%

    No Known Activations