© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128877
    Prev
    Next
    INDEX
    Explanations

    occurrences of elements or placeholder symbols in programming code

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
     ſche
    -0.91
     increí
    -0.85
    majánló
    -0.81
     ſch
    -0.79
     queſta
    -0.77
    ſelves
    -0.76
     desmotivaciones
    -0.75
    ſelf
    -0.74
    verifyException
    -0.74
    SequentialGroup
    -0.73
    POSITIVE LOGITS
        
    0.45
    IBOutlet
    0.43
    public
    0.43
    Override
    0.41
    SerializeField
    0.40
    IBAction
    0.38
    protected
    0.38
            
    0.36
    Autowired
    0.34
                    
    0.34
    Activations Density 0.004%

    No Known Activations