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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1705
    Prev
    Next
    INDEX
    Explanations

    code snippets related to web development or JavaScript functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTLD
    -0.77
    __':
    
    -0.74
    complexContent
    -0.72
    principalColumn
    -0.71
    MessageTagHelper
    -0.71
    MemoryWarning
    -0.71
    protoc
    -0.70
    httphttps
    -0.70
    DeleteBehavior
    -0.69
    StoryboardSegue
    -0.69
    POSITIVE LOGITS
    <bos>
    0.60
    "]').
    0.55
    ']").
    0.50
    LElement
    0.50
    ?>"
    0.49
    ')}}
    0.48
     Whig
    0.46
    ');?>
    0.45
    ])))
    0.45
    })$}
    0.45
    Activations Density 0.240%

    No Known Activations