© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 465
    Prev
    Next
    INDEX
    Explanations

    emotions and their impact on relationships and experiences

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

    emotional words and phrases related to inner feelings like joy, happiness, suffering, peace, and insight.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inatal
    -0.43
     gine
    -0.42
     FLOR
    -0.40
     expend
    -0.39
    TableAdapter
    -0.39
     Szer
    -0.39
     Mariana
    -0.39
     Ry
    -0.38
     independent
    -0.38
    Independent
    -0.38
    POSITIVE LOGITS
     pleaſure
    0.68
     Hitze
    0.60
     kekerasan
    0.59
     Nachhaltigkeit
    0.58
     Vergnügen
    0.57
     CreateTagHelper
    0.57
    fulness
    0.54
    ">//
    0.54
    tagHelperRunner
    0.54
    fasis
    0.54
    Activations Density 0.389%

    No Known Activations