© 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. 5-GEMMASCOPE-RES-16K
    6. 6735
    Prev
    Next
    INDEX
    Explanations

    specific structural elements or syntax commonly found in programming or data serialization

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

    punctuation marks and structural elements in code or text

    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
    bos
    -0.67
    Pyx
    -0.62
     McLeod
    -0.62
    슬
    -0.60
    aka
    -0.60
     Ayres
    -0.59
    tinyos
    -0.59
     mole
    -0.58
     Che
    -0.58
     Meisters
    -0.58
    POSITIVE LOGITS
    __":
    
    1.44
    __':
    
    1.28
    }>;
    1.24
    __":
    1.22
    __':
    1.13
    }();
    1.07
    ())));
    1.07
    "]));
    1.04
    ]")]
    1.03
    ]';
    1.03
    Activations Density 0.216%

    No Known Activations