© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9178
    Prev
    Next
    INDEX
    Explanations

    phrases and determiners that indicate identity or specification

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

    "This", "that", "these" at the start of a sentence

    np_acts-logits-general · gemini-2.0-flash

    demonstratives and first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.55
     utafitiHapana
    -0.52
    发表于
    -0.49
    Rozm
    -0.42
    MLLoader
    -0.41
    mingen
    -0.40
     LEA
    -0.40
    ArrowToggle
    -0.39
    gige
    -0.39
    riu
    -0.39
    POSITIVE LOGITS
     kind
    0.49
    WriteTagHelper
    0.48
     pel
    0.45
     defaultstate
    0.43
    Билгалдахарш
    0.42
     circonst
    0.39
    assertj
    0.38
     partido
    0.38
     indeed
    0.37
    EndProject
    0.36
    Activations Density 0.205%

    No Known Activations