© 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. 3865
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "know" and related queries about knowledge or understanding

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

    Followed by conditional words ("if", "to")

    np_acts-logits-general · gemini-2.0-flash

    verb + complement phrases

    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
     resourceCulture
    -0.53
     становника
    -0.47
     kasarigan
    -0.45
     Bellini
    -0.44
    ポチ
    -0.41
    軽量
    -0.41
    tonode
    -0.41
    MessageTagHelper
    -0.41
     endwhile
    -0.40
    zbęd
    -0.39
    POSITIVE LOGITS
     cherchés
    0.44
     anymore
    0.43
    konomi
    0.42
     Савезне
    0.41
     about
    0.41
     whether
    0.41
    Myself
    0.40
     genetics
    0.40
     beginnetje
    0.40
    genetics
    0.40
    Activations Density 0.117%

    No Known Activations