© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 10715
    Prev
    Next
    INDEX
    Explanations

    references to decision-making and evaluations based on criteria or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.54
    DispatchToProps
    -0.49
    illeurs
    -0.47
     kawaida
    -0.44
     Curi
    -0.44
    ssan
    -0.43
    ostoma
    -0.43
     Roskov
    -0.43
    IAm
    -0.42
    ]++;
    -0.41
    POSITIVE LOGITS
     based
    3.02
     Based
    2.64
     BASED
    2.58
    Based
    2.49
    based
    2.37
    BASED
    2.11
     basé
    2.07
     basing
    2.07
     baseado
    2.06
     basado
    2.05
    Activations Density 1.100%

    No Known Activations