© 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. 3-GEMMASCOPE-RES-16K
    11. 12661
    Prev
    Next
    INDEX
    Explanations

    statements about honesty and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.79
    paramref
    -0.52
    ))]
    -0.52
    }));
    -0.50
    Портал
    -0.49
    TestBed
    -0.47
     Boch
    -0.45
    </em>
    -0.45
    )));
    -0.44
     }));
    -0.44
    POSITIVE LOGITS
     DialogInterface
    0.77
     Roskov
    0.76
     disambiguazione
    0.74
     kidding
    0.74
    SequentialGroup
    0.74
    MemoryWarning
    0.72
     Савезне
    0.70
     SqlParameter
    0.70
    Personendaten
    0.68
     Wiktionnaire
    0.66
    Activations Density 0.199%

    No Known Activations