© 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. 4560
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and social connections

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

    Past tense of thinking/feeling verbs

    np_acts-logits-general · gemini-2.0-flash

    I knew that

    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
     is
    -0.59
     obecnie
    -0.58
     currently
    -0.57
     are
    -0.56
    currently
    -0.54
     yoktur
    -0.53
    #+#
    -0.53
     becomes
    -0.52
     feels
    -0.51
    ifies
    -0.51
    POSITIVE LOGITS
     was
    1.00
     had
    0.92
     hadn
    0.85
     knew
    0.84
     seemed
    0.84
    していました
    0.81
    ıyordu
    0.80
     lacked
    0.79
     vardı
    0.77
     había
    0.76
    Activations Density 3.310%

    No Known Activations