© 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. 5-GEMMASCOPE-RES-16K
    11. 6351
    Prev
    Next
    INDEX
    Explanations

    references to living spaces, particularly living rooms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -1.03
    InSection
    -0.84
    chaun
    -0.78
    DataPropertyName
    -0.74
     ModelExpression
    -0.74
     Kurds
    -0.74
    })).
    -0.73
    +#+
    -0.72
    Hermes
    -0.72
    __":
    -0.71
    POSITIVE LOGITS
     living
    2.39
     Living
    2.29
    Living
    2.18
     LIVING
    2.10
    living
    2.08
    LIVING
    1.90
     liv
    1.27
     Livingston
    1.26
     vivant
    1.18
     live
    1.14
    Activations Density 0.045%

    No Known Activations