© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3534
    Prev
    Next
    INDEX
    Explanations

    content related to political nominations and judicial appointments

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

    "appoint" or "selected"

    np_acts-logits-general · gemini-2.0-flash

    judges and nominees appointment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.58
     CURIAM
    -0.56
     ABSTRACT
    -0.50
     оригіналу
    -0.48
    luiting
    -0.47
     Мексичка
    -0.47
     AssemblyCulture
    -0.46
    tagHelperRunner
    -0.46
     acoustic
    -0.45
     amplific
    -0.45
    POSITIVE LOGITS
     appointing
    1.49
     appoint
    1.43
     appointment
    1.41
     appointed
    1.36
     appoints
    1.26
     appointments
    1.24
     APPOINT
    1.23
     Appointments
    1.20
     Appointment
    1.18
     selection
    1.15
    Activations Density 0.483%

    No Known Activations