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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 14157
    Prev
    Next
    INDEX
    Explanations

    sections of text that do not contain meaningful content or relevant information

    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
     "/";
    -0.50
     '/';
    -0.49
    SizeMode
    -0.48
    quelize
    -0.48
     Oester
    -0.47
    ;"><
    -0.47
    (${
    -0.47
     giac
    -0.46
     textStatus
    -0.45
    uya
    -0.44
    POSITIVE LOGITS
    __':
    
    0.97
     Audiodateien
    0.87
     initComponents
    0.87
    ]
    0.87
    }]
    0.86
     CURIAM
    0.85
     estekak
    0.85
    __":
    0.84
    __":
    
    0.83
    ″]
    0.82
    Activations Density 0.013%

    No Known Activations