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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 35749
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of reconstruction and estimation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    reconstructing data, shapes, or vision

    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
    Not in Any Lists

    No Comments

    Negative Logits
     onder
    -0.39
     confluence
    -0.38
    InstrumentedTest
    -0.37
     veto
    -0.36
    нциклопе
    -0.35
    Rounded
    -0.35
     sopra
    -0.35
     encar
    -0.34
     cis
    -0.34
     pips
    -0.34
    POSITIVE LOGITS
     reconstruct
    0.93
     reconstruction
    0.90
     reconstructions
    0.84
     Reconstruction
    0.82
     reconstructed
    0.81
     reconstru
    0.81
    Reconstruction
    0.73
    重建
    0.71
     rekon
    0.69
     restoration
    0.64
    Activations Density 0.187%

    No Known Activations