© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 8871
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs indicating actions or intentions

    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
     nakalista
    -0.55
    fjspx
    -0.52
    featureID
    -0.49
    DeleteBehavior
    -0.48
    ftagPool
    -0.46
    EDEFAULT
    -0.45
     userEmail
    -0.44
     okuyayım
    -0.43
    UserScript
    -0.42
     {?}
    -0.41
    POSITIVE LOGITS
     enable
    0.88
     allow
    0.84
     help
    0.83
     ensure
    0.82
     facilitate
    0.75
     accompany
    0.71
     assure
    0.69
     accommodate
    0.66
     aid
    0.65
     prevent
    0.63
    Activations Density 0.466%

    No Known Activations