© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 8204
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "manifestation" and its variations

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

    manifest and manifestation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.65
     المعيارى
    -0.61
     Anſ
    -0.57
     SQLException
    -0.56
    ſelves
    -0.54
     Efq
    -0.53
    peas
    -0.51
     alibi
    -0.51
     Reſ
    -0.51
    byes
    -0.51
    POSITIVE LOGITS
     Manifest
    0.99
    Manifest
    0.97
    manifest
    0.96
     manifesting
    0.91
     manifestation
    0.91
     manifest
    0.89
     manifested
    0.87
    IFEST
    0.84
     Manif
    0.83
     manifests
    0.81
    Activations Density 0.007%

    No Known Activations