© 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. 22-GEMMASCOPE-RES-16K
    11. 5598
    Prev
    Next
    INDEX
    Explanations

    references to meetings, hearings, and formal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Events such as meetings and hearings

    np_acts-logits-general · gemini-2.0-flash

    meetings and hearings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }))
    -0.73
    MigrationBuilder
    -0.71
    ])).
    -0.67
    ]));
    -0.66
    ]))
    -0.65
     ddelweddau
    -0.63
    $}}
    -0.63
     MainAxisSize
    -0.62
    })).
    -0.61
    ]").
    -0.60
    POSITIVE LOGITS
     held
    1.09
     conducted
    1.08
     attended
    0.99
     hosted
    0.91
     involving
    0.85
    conducted
    0.85
     organized
    0.79
     Conducted
    0.77
    Held
    0.77
     organised
    0.76
    Activations Density 0.470%

    No Known Activations