© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 6717
    Prev
    Next
    INDEX
    Explanations

    elements of vivid and descriptive imagery related to physical states and sensations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     series
    -0.52
    ことがある
    -0.52
     (
    -0.52
     “
    -0.51
     personnal
    -0.49
     actually
    -0.49
     "
    -0.49
     traditionally
    -0.49
    hez
    -0.49
     Robert
    -0.48
    POSITIVE LOGITS
    writeFieldEnd
    0.74
     Anis
    0.72
    Tikang
    0.72
     Numerade
    0.69
    MockMvc
    0.68
    tagext
    0.66
     utafitiHapana
    0.64
    EnableWeb
    0.63
     елның
    0.63
     Telex
    0.62
    Activations Density 0.290%

    No Known Activations