Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15698
    Prev
    Next
    INDEX
    Explanations

    terms related to subjective assessments and opinions

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

    Statements of opinion or subjectivity

    np_acts-logits-general · gemini-2.0-flash

    subjective determination of opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     leaſt
    -0.44
    menuStrip
    -0.44
     CreateTagHelper
    -0.44
    wiſe
    -0.41
    ſelves
    -0.40
     greateſt
    -0.37
    𝟸
    -0.37
    ualaikum
    -0.35
     preoc
    -0.35
    Démographie
    -0.35
    POSITIVE LOGITS
     subjective
    1.84
     subjek
    1.43
     subjectivity
    1.38
     subjec
    1.37
     subje
    1.20
     sogget
    1.16
     субъек
    1.13
     personal
    0.92
    jective
    0.90
     SUBJECT
    0.84
    Activations Density 0.429%

    No Known Activations