© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 462
    Prev
    Next
    INDEX
    Explanations

    the concept of "level" in various contexts

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

    "level of"

    np_acts-logits-general · gemini-2.0-flash

    level of

    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
    انيف
    -0.85
     StringTokenizer
    -0.84
    ")));
    
    -0.83
     otomatig
    -0.77
    IUrlHelper
    -0.76
     estekak
    -0.75
    FunctionFlags
    -0.75
     виправивши
    -0.75
     wireType
    -0.74
    ]));
    
    -0.73
    POSITIVE LOGITS
     LEVEL
    1.02
     levels
    0.99
    LEVEL
    0.96
    Levels
    0.96
     Level
    0.96
     Levels
    0.93
     level
    0.88
    level
    0.87
    levels
    0.86
    Level
    0.82
    Activations Density 0.096%

    No Known Activations