© 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. 31-GEMMASCOPE-RES-16K
    11. 2595
    Prev
    Next
    INDEX
    Explanations

    phrases related to judicial appointments and elections

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

    references to judicial appointments and the distinction between appointed and elected positions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.45
    matchCondition
    -0.43
     Normdatei
    -0.40
    Referencer
    -0.39
    RTDA
    -0.37
    SerializedSize
    -0.36
    قایناق‌لار
    -0.35
    ihnachten
    -0.34
     berätt
    -0.34
    ErrUnexpectedEOF
    -0.33
    POSITIVE LOGITS
     appointed
    2.22
     appointment
    2.05
     appoint
    2.02
     appointing
    1.93
     APPOINT
    1.82
     Appointed
    1.80
     Appointment
    1.76
    appointed
    1.76
     appoints
    1.68
     appointments
    1.67
    Activations Density 0.586%

    No Known Activations