© 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. 28-GEMMASCOPE-RES-16K
    6. 4423
    Prev
    Next
    INDEX
    Explanations

    phrases indicating studies, analyses, or clinical evaluations

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

    "In", "This", or "The" at the start of sentences/sections

    np_acts-logits-general · gemini-2.0-flash

    in THIS section

    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
     moreover
    -0.63
    expandindo
    -0.62
     inoltre
    -0.60
     Inoltre
    -0.60
    brigens
    -0.58
    Inoltre
    -0.56
     dessutom
    -0.55
     furthermore
    -0.53
     außerdem
    -0.52
    writeFieldEnd
    -0.52
    POSITIVE LOGITS
    ostante
    0.69
     المعيارى
    0.47
    يميديا
    0.47
    withstanding
    0.45
    isser
    0.42
    adecimal
    0.41
    orious
    0.41
     simplest
    0.40
    itudinal
    0.40
    middels
    0.39
    Activations Density 0.513%

    No Known Activations