© 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. 20-GEMMASCOPE-RES-16K
    11. 14580
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvements and progress

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

    phrases signaling improvement or upward change—recovery, increases, or positive outcomes, often in comparative or metric contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
     дописавши
    -0.49
     buff
    -0.43
    OGND
    -0.43
    Personendaten
    -0.41
    getWriter
    -0.40
     ſtre
    -0.39
    rophi
    -0.39
    AddTagHelper
    -0.38
     Diſ
    -0.38
     war
    -0.37
    POSITIVE LOGITS
     but
    0.79
     nhưng
    0.75
     namun
    0.73
     pero
    0.73
     tapi
    0.67
     però
    0.65
     mutta
    0.64
    但
    0.64
     But
    0.63
    But
    0.63
    Activations Density 0.421%

    No Known Activations