© 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. 21-GEMMASCOPE-RES-16K
    11. 1418
    Prev
    Next
    INDEX
    Explanations

    references to entities or individuals in contexts of fleeing or escaping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.93
    Kaynakça
    -0.84
    oneofs
    -0.79
    AddTagHelper
    -0.79
    )();
    -0.75
    OGND
    -0.73
    )++;
    -0.72
     متعلقه
    -0.70
    Jeografia
    -0.69
     defaultstate
    -0.68
    POSITIVE LOGITS
    muo
    0.52
    ……
    0.50
    ——
    0.47
    Arri
    0.47
     gaze
    0.44
    —-
    0.44
     Waiting
    0.44
     sentient
    0.43
    —
    0.43
     conci
    0.43
    Activations Density 0.030%

    No Known Activations