© 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. 8-GEMMASCOPE-RES-16K
    6. 15415
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols used in formatting or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.61
    دانشنامهٔ
    -0.60
     Bourgoin
    -0.60
    RegressionTest
    -0.60
    ensement
    -0.60
     ban
    -0.59
     kere
    -0.57
    тья
    -0.57
     kasarigan
    -0.57
     noten
    -0.56
    POSITIVE LOGITS
     Houſe
    0.88
     aikaa
    0.84
     Anſ
    0.83
    bibfield
    0.83
    ]--;
    0.82
    ='';
    
    0.82
    ſelf
    0.81
    ]='\
    0.81
     Lithuan
    0.78
     Diſ
    0.78
    Activations Density 0.563%

    No Known Activations