© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 810
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.65
    mappedBy
    -0.58
    ]")]
    -0.57
     चीज़ों
    -0.53
    OGND
    -0.53
     queſta
    -0.51
    ogly
    -0.49
    BrowserRouter
    -0.48
    )";
    
    -0.46
    KommentareTeilen
    -0.46
    POSITIVE LOGITS
     peers
    0.71
     surroundings
    0.63
     neighbors
    0.59
     neighbours
    0.57
     countrymen
    0.56
     ancestors
    0.55
     enemies
    0.53
     contemporaries
    0.53
     loved
    0.52
     amado
    0.52
    Activations Density 0.320%

    No Known Activations