Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6981
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and class attributes within a document structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    
    -1.39
    ########.
    -1.38
    TagMode
    -1.37
    )});
    -1.33
    __':
    
    -1.32
    ])));
    -1.29
    contentLoaded
    -1.28
    ]));
    
    -1.28
    ]})
    -1.28
    Vidite
    -1.27
    POSITIVE LOGITS
    -
    1.28
     a
    0.79
    ,
    0.76
     the
    0.74
     and
    0.61
    0
    0.59
     of
    0.56
     -
    0.56
     an
    0.54
     for
    0.53
    Activations Density 0.551%

    No Known Activations