Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10296
    Prev
    Next
    INDEX
    Explanations

    mentions of modules, indicating a focus on programming or software development contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.78
    INSEE
    -0.59
    RegistryLite
    -0.56
    InjectAttribute
    -0.53
    windowFixed
    -0.53
    RRect
    -0.52
    PyExc
    -0.52
    toMatchSnapshot
    -0.52
    AnchorTagHelper
    -0.51
    ApiModelProperty
    -0.51
    POSITIVE LOGITS
    module
    2.44
     module
    1.09
    Module
    0.98
     Module
    0.84
     MODULE
    0.74
    NgModule
    0.70
    odule
    0.68
    })();
    
    0.66
     akka
    0.65
    googleapis
    0.64
    Activations Density 0.170%

    No Known Activations