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. 1-GEMMASCOPE-RES-16K
    6. 5981
    Prev
    Next
    INDEX
    Explanations

    frequent use of the word "mostly"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    లాలు
    -0.94
    SpringBootTest
    -0.79
    jspx
    -0.78
     esternos
    -0.77
     препратки
    -0.72
    });*/
    -0.72
    yntaxException
    -0.72
    省市镇
    -0.68
     intptr
    -0.68
    fjspx
    -0.66
    POSITIVE LOGITS
     sobre
    0.90
    MOST
    0.83
    contro
    0.82
    most
    0.76
     Most
    0.76
    Most
    0.73
     contro
    0.70
     Contro
    0.65
    bcrypt
    0.65
    sobre
    0.63
    Activations Density 0.073%

    No Known Activations