© 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. 9-GEMMASCOPE-RES-131K
    11. 58575
    Prev
    Next
    INDEX
    Explanations

    references to the term "lash" and its derivatives, often in a context related to criticism or physical items like eyelash curlers

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

    lashes out, backlash, eyelashes, Lashkar

    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
    enumi
    -0.47
    OGND
    -0.45
     COE
    -0.44
    enumii
    -0.42
    CRC
    -0.42
    cstdio
    -0.42
     CRC
    -0.41
     univ
    -0.41
     gud
    -0.40
     désolés
    -0.40
    POSITIVE LOGITS
     lash
    1.98
     lashes
    1.91
     Lash
    1.85
     lashed
    1.56
    lash
    1.45
     eyelashes
    1.27
    elashes
    1.16
     eyelash
    1.15
    lashes
    1.12
    lashed
    1.09
    Activations Density 0.005%

    No Known Activations