© 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. 19-GEMMASCOPE-RES-16K
    11. 11065
    Prev
    Next
    INDEX
    Explanations

    phrases that involve comparisons or similes

    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
    Према
    -0.64
     kaarangay
    -0.56
    ]-->
    -0.56
     Signalez
    -0.56
     OnTriggerEnter
    -0.53
    ]=>
    -0.53
    Newswire
    -0.51
    ]")]
    -0.50
    
    -0.48
     mergeFrom
    -0.48
    POSITIVE LOGITS
     traditionnelle
    0.63
     seolah
    0.62
     sauvages
    0.62
     manière
    0.62
     sauvage
    0.61
    wijl
    0.60
     they
    0.59
     we
    0.58
     façon
    0.56
     chaude
    0.56
    Activations Density 0.180%

    No Known Activations