© 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. 23-GEMMASCOPE-RES-16K
    6. 11864
    Prev
    Next
    INDEX
    Explanations

    HTML or markup tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -1.30
    </strong>
    -1.27
     fl
    -1.12
    <em>
    -1.08
    fl
    -1.06
    ",@"
    -0.93
    """
    
    -0.91
    <strong>
    -0.91
     
    -0.90
     """
    
    -0.88
    POSITIVE LOGITS
    </b>
    2.47
    </i>
    2.23
    <i>
    1.58
    <b>
    1.50
    dfrac
    1.20
    </td>
    0.96
    '>
    0.94
    ']").
    0.93
    '>"
    0.89
     + 
    0.88
    Activations Density 0.094%

    No Known Activations