© 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
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15886
    Prev
    Next
    INDEX
    Explanations

    instances of the word "familiar" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JvmStatic
    -0.45
     utafitiHapana
    -0.44
    //
    -0.42
    TestMethod
    -0.40
    hpp
    -0.40
     forceps
    -0.39
     Meksiku
    -0.39
    ьаж
    -0.38
     stroke
    -0.37
     soins
    -0.37
    POSITIVE LOGITS
     familiar
    2.86
    familiar
    2.61
    Familiar
    2.53
     Familiar
    2.48
     familiarity
    2.16
     familiarize
    1.82
    熟悉
    1.75
    熟悉的
    1.66
     unfamiliar
    1.65
     familiare
    1.63
    Activations Density 0.157%

    No Known Activations