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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9585
    Prev
    Next
    INDEX
    Explanations

    escape characters and special formatting symbols in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    -0.72
    (
    -0.60
      
    -0.57
    <sup>
    -0.56
    ↵
    -0.55
        
    -0.51
       
    -0.51
    "
    -0.50
    </td>
    -0.49
    ist
    -0.47
    POSITIVE LOGITS
     \$
    0.93
    OGND
    0.82
     $\$
    0.82
    ..\
    0.76
     Administrativna
    0.75
     "\\
    0.74
     :\
    0.73
     noDo
    0.72
     Wikimedijinoj
    0.72
     (\
    0.71
    Activations Density 1.508%

    No Known Activations