© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 7590
    Prev
    Next
    INDEX
    Explanations

    references to "step" in various contexts, indicating movement, relationships, or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "])
    
    -0.94
     Barbier
    -0.88
    }});
    -0.85
    tahankan
    -0.85
    |}{}
    -0.82
     Aner
    -0.78
     všem
    -0.78
     Pala
    -0.77
     Ärz
    -0.77
    }$}
    -0.76
    POSITIVE LOGITS
     STEP
    2.16
     step
    2.05
     Step
    2.01
    Step
    1.96
     steps
    1.91
    step
    1.86
    STEP
    1.84
     Steps
    1.84
     STEPS
    1.74
     stepping
    1.66
    Activations Density 0.040%

    No Known Activations