© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 3850
    Prev
    Next
    INDEX
    Explanations

    references to cloud computing and related technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rifles
    -1.04
     @"/
    -0.96
     مشين
    -0.90
     Mérimée
    -0.89
     NgModule
    -0.87
     lances
    -0.86
     termica
    -0.85
    ]")]
    -0.84
     Ennis
    -0.84
     joaat
    -0.83
    POSITIVE LOGITS
     Cloud
    1.40
     cloud
    1.37
    cloud
    1.35
     clouds
    1.26
     CLOUD
    1.24
    Cloud
    1.21
    CLOUD
    1.16
     Clouds
    1.10
    clouds
    1.10
    Clouds
    1.00
    Activations Density 0.067%

    No Known Activations