© 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. 28-GEMMASCOPE-RES-16K
    11. 7764
    Prev
    Next
    INDEX
    Explanations

    concepts related to human connections and personal experiences

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

    Followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    I and we

    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
    出版年
    -0.51
     <<<<<<<<<<<<<<
    -0.47
    webElementXpaths
    -0.45
     незавершена
    -0.44
    IMDG
    -0.43
     المعيارى
    -0.42
     يتيمه
    -0.42
     Exactos
    -0.42
    fören
    -0.41
    iete
    -0.40
    POSITIVE LOGITS
     I
    1.42
     we
    1.16
    We
    0.66
    私は
    0.65
     나는
    0.65
     мы
    0.60
    僕は
    0.60
     We
    0.59
    小编
    0.58
    我都
    0.58
    Activations Density 0.849%

    No Known Activations