© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11598
    Prev
    Next
    INDEX
    Explanations

    terms related to performance, transformation, and duplication in artistic or cinematic contexts

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

    likeness or imitation

    np_acts-logits-general · gemini-2.5-flash-lite

    words for impersonation, doubling, or shape-changing (e.g., impersonator, double, shift/shape/shifted).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    SourceChecksum
    -0.59
    Cyfarwyddwr
    -0.54
    phazard
    -0.46
    indelijk
    -0.44
    inander
    -0.44
    sprüng
    -0.43
    NameInMap
    -0.43
     يتيمه
    -0.43
     propOrder
    -0.42
     Stellung
    -0.41
    POSITIVE LOGITS
     likeness
    0.58
     imperson
    0.58
     imitation
    0.54
     mimic
    0.54
     imitate
    0.54
     resemblance
    0.53
     imit
    0.53
     clone
    0.52
     Imit
    0.51
     Imitation
    0.51
    Activations Density 0.261%

    No Known Activations