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. 7-GEMMASCOPE-RES-16K
    6. 11688
    Prev
    Next
    INDEX
    Explanations

    the presence of specific characters and punctuation within the text

    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
    ")))
    -0.71
    ]")]
    -0.68
    "]))
    -0.66
    ")));
    
    -0.64
    "]));
    -0.64
    "))
    
    -0.64
    ")));
    -0.61
    "));
    
    -0.56
    "))
    -0.56
    ())))
    -0.54
    POSITIVE LOGITS
     AssemblyCompany
    0.95
    OGND
    0.90
    PreferredItem
    0.81
     beginnetje
    0.77
    Portale
    0.74
     ©️
    0.72
     виправивши
    0.69
    NameInMap
    0.68
    تقاوى
    0.68
    pherals
    0.66
    Activations Density 0.514%

    No Known Activations