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. 18-GEMMASCOPE-RES-16K
    6. 728
    Prev
    Next
    INDEX
    Explanations

    print statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    `System.out.println`

    np_acts-logits-general · gemini-2.0-flash

    System.out.println output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.74
    ()]);
    -0.71
    ]=="
    -0.69
    élie
    -0.68
    ]!='
    -0.66
    ']=='
    -0.65
    "}")
    -0.65
    %;
    
    -0.65
    ()));
    
    -0.64
    SharedDtor
    -0.64
    POSITIVE LOGITS
    println
    0.76
    Println
    0.63
     println
    0.63
     RouterModule
    0.58
     AssemblyCompany
    0.55
    MemoryWarning
    0.54
    MethodManager
    0.54
     OnInit
    0.53
    ContentAlignment
    0.52
     Corinth
    0.51
    Activations Density 0.011%

    No Known Activations