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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2118
    Prev
    Next
    INDEX
    Explanations

    structures and elements in code or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    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>
    -1.31
    <i>
    -1.10
    <strong>
    -1.05
    <b>
    -0.90
    <u>
    -0.87
    ***
    -0.57
    <sub>
    -0.55
     ($\
    -0.53
    <code>
    -0.51
    **
    -0.50
    POSITIVE LOGITS
    ↵
    0.72
    SourceChecksum
    0.71
    URLException
    0.66
     }
    0.65
     }));
    0.64
     }))
    0.61
    </tbody>
    0.61
     */}
    0.59
    BufferException
    0.58
    </td>
    0.57
    Activations Density 0.024%

    No Known Activations