© 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. 33-GEMMASCOPE-RES-16K
    11. 11773
    Prev
    Next
    INDEX
    Explanations

    aspects related to self-improvement and personal affirmation

    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
    TagMode
    -0.43
    帖最后由
    -0.43
     TextInputType
    -0.39
     leaft
    -0.38
     ſta
    -0.37
     ſche
    -0.36
     najczęściej
    -0.36
    tableFuture
    -0.36
     myſelf
    -0.35
    featureID
    -0.35
    POSITIVE LOGITS
     good
    2.86
    good
    2.39
     excellent
    2.30
    excellent
    2.06
     GOOD
    2.02
     goede
    1.97
     хоро
    1.88
    Good
    1.87
     gute
    1.84
     buenas
    1.80
    Activations Density 1.044%

    No Known Activations