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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 56218
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate error messages or query-like statements

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

    Japanese question endings and English tracebacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </table>
    -0.57
    </h5>
    -0.43
     Ehr
    -0.40
    </h4>
    -0.40
     rechter
    -0.38
     zapal
    -0.38
    ↵↵↵
    -0.37
    Incl
    -0.37
     uncontrollable
    -0.36
    </i>
    -0.36
    POSITIVE LOGITS
    는
    1.13
    은
    0.81
    나는
    0.73
    이는
    0.71
     것은
    0.69
     는
    0.68
    하는
    0.68
    되는
    0.66
    리는
    0.65
     ſind
    0.64
    Activations Density 0.001%

    No Known Activations