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
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 950
    Prev
    Next
    INDEX
    Explanations

    sentences expressing personal reflections and opinions

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

    Sentences ending with a statement of opinion or feeling

    np_acts-logits-general · gemini-2.0-flash

    opinions and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.84
    AddTagHelper
    -0.79
     createState
    -0.75
    setVerticalGroup
    -0.73
     виправивши
    -0.72
    ⟬
    -0.72
    RTEX
    -0.71
    Hentet
    -0.71
    MigrationBuilder
    -0.70
    bootstrapcdn
    -0.69
    POSITIVE LOGITS
     wish
    0.27
     merasa
    0.26
    というと
    0.26
     feel
    0.25
     feeling
    0.24
    I
    0.24
     agree
    0.24
     recherches
    0.23
     hoping
    0.23
    agree
    0.23
    Activations Density 0.454%

    No Known Activations