© 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. 7693
    Prev
    Next
    INDEX
    Explanations

    conjugated forms of the verb "to be" and variations of "is" or "was" used in different 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
    parsedMessage
    -0.82
     myſelf
    -0.63
    ंदीखरीदारी
    -0.59
    ſelves
    -0.55
    ſelf
    -0.53
    PerformLayout
    -0.53
    MessageOf
    -0.53
     purpoſe
    -0.50
    Бахар
    -0.49
     themſelves
    -0.49
    POSITIVE LOGITS
     like
    0.67
     important
    0.65
     about
    0.62
     part
    0.60
     frustrating
    0.56
     handlar
    0.56
     something
    0.54
     scary
    0.52
     gratifying
    0.50
     reminiscent
    0.49
    Activations Density 0.210%

    No Known Activations