© 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. 10-GEMMASCOPE-RES-16K
    11. 16002
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs, including variables and data types, especially in the context of functions and object definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *{
    -0.56
     annual
    -0.53
    StoryboardSegue
    -0.52
    ]--;
    -0.52
    setcounter
    -0.50
    }))
    -0.50
    BarItem
    -0.49
    =[];
    -0.48
    annual
    -0.47
    __':
    -0.47
    POSITIVE LOGITS
     StringTokenizer
    0.83
     String
    0.77
     '\\;'
    0.75
     StringField
    0.75
    classnames
    0.72
    String
    0.70
     txt
    0.70
     strings
    0.69
     NSString
    0.68
    WriteTagHelper
    0.68
    Activations Density 1.017%

    No Known Activations