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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 519
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and syntactic structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.90
    DebuggerStep
    -0.70
    basicConfig
    -0.66
     mapStateToProps
    -0.60
     nah
    -0.59
     VIAF
    -0.59
    waitKey
    -0.58
    Nah
    -0.58
     RESP
    -0.58
    Personendaten
    -0.58
    POSITIVE LOGITS
    endphp
    0.54
    ільки
    0.51
     S
    0.51
     kandungan
    0.49
    ]))
    
    0.49
    ])):
    0.48
     Réponses
    0.48
     céramique
    0.48
     énergétique
    0.47
     commerciali
    0.46
    Activations Density 0.104%

    No Known Activations