© 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. 5-GEMMASCOPE-RES-16K
    6. 602
    Prev
    Next
    INDEX
    Explanations

    references to levels in structured data contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -1.09
    "):
    
    -0.87
    ]]);
    -0.86
    :{}
    -0.85
    ]$}
    -0.83
    ]));
    
    -0.83
    </>
    
    -0.83
     Gorman
    -0.82
    __":
    
    -0.82
    polation
    -0.81
    POSITIVE LOGITS
     level
    2.32
     LEVEL
    2.28
     Level
    2.21
    level
    2.21
    Level
    2.10
    LEVEL
    2.08
     levels
    2.01
    levels
    1.86
     Levels
    1.84
    Levels
    1.79
    Activations Density 0.079%

    No Known Activations