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. 2-GEMMASCOPE-RES-16K
    6. 4832
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and structures in marine environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.86
    CloseOperation
    -0.79
    protoimpl
    -0.75
    ngdoc
    -0.68
    twimg
    -0.65
    nonatomic
    -0.65
     nonatomic
    -0.65
    =?";
    -0.64
    .*")]
    -0.63
     StatelessWidget
    -0.63
    POSITIVE LOGITS
    UrlResolution
    0.51
    ellees
    0.48
    readFileSync
    0.46
    NgModule
    0.41
    enment
    0.41
     embal
    0.41
    mainloop
    0.41
    جغرافيا
    0.41
    KEYCODE
    0.40
     ControllerBase
    0.40
    Activations Density 0.208%

    No Known Activations