© 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. 12-GEMMASCOPE-RES-16K
    6. 3694
    Prev
    Next
    INDEX
    Explanations

    words associated with providing instructions or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.66
    richTextPanel
    -0.56
     flies
    -0.55
    Geplaatst
    -0.54
     AssemblyCompany
    -0.51
     bearer
    -0.51
     setDescription
    -0.51
    แทน
    -0.50
     resourceCulture
    -0.49
     avatar
    -0.49
    POSITIVE LOGITS
     also
    0.63
     kèm
    0.61
    ']))
    
    0.59
    ceğini
    0.58
     subsequent
    0.58
     eventual
    0.56
     Administrativna
    0.54
     other
    0.54
    '))
    
    0.53
    "]);
    
    0.53
    Activations Density 0.509%

    No Known Activations