© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14501
    Prev
    Next
    INDEX
    Explanations

    notions of justice and deserved recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "deserve," "deserves," "deserving," or "deserved."

    np_acts-logits-general · gemini-2.0-flash

    deserve or earned recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.42
    ScopeManager
    -0.40
    IntoConstraints
    -0.39
    .*")]
    -0.38
    DMETHOD
    -0.36
    ếng
    -0.35
     Ause
    -0.34
     contraire
    -0.33
     كث
    -0.32
    })+
    -0.32
    POSITIVE LOGITS
     deserve
    2.02
     deserving
    1.97
     deserved
    1.96
     deserves
    1.87
    deserved
    1.57
     verdient
    1.54
     mérit
    1.49
     earned
    1.46
     merit
    1.45
     merec
    1.40
    Activations Density 0.380%

    No Known Activations