© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 16053
    Prev
    Next
    INDEX
    Explanations

    phrases indicating goals, aims, or intentions within texts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     بيها
    -0.66
    Jereo
    -0.59
    Демографія
    -0.58
    +#+
    -0.55
    TemporalType
    -0.54
    出版年
    -0.54
    ロウィン
    -0.54
    (!__
    -0.52
     ringer
    -0.52
    ristmas
    -0.50
    POSITIVE LOGITS
     aims
    1.53
     hopes
    1.48
     Aims
    1.17
     goals
    1.10
     plans
    1.08
     desires
    1.07
     concerns
    1.07
     claims
    1.05
     intentions
    1.03
     objectives
    1.02
    Activations Density 0.147%

    No Known Activations