© 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. 36-GEMMASCOPE-RES-16K
    6. 15959
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and nouns associated with possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }}_{\
    -0.37
     HttpNotFound
    -0.35
    WSTR
    -0.35
    Enders
    -0.33
     Journalists
    -0.33
     Authors
    -0.32
     feit
    -0.32
    .*")]
    -0.31
    ContentAsync
    -0.31
    }}_{
    -0.31
    POSITIVE LOGITS
     approach
    0.84
     expertise
    0.83
     efforts
    0.73
    approach
    0.69
     abordagem
    0.69
     contribution
    0.67
     vision
    0.67
     influence
    0.66
     passion
    0.65
     mission
    0.65
    Activations Density 0.511%

    No Known Activations