© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12628
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experience and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.61
    లాలు
    -0.57
     rospy
    -0.54
     propOrder
    -0.53
    IsMutable
    -0.52
    تقاوى
    -0.52
    ագրություններ
    -0.51
    :]:
    -0.51
    theless
    -0.50
    Хьажоргаш
    -0.50
    POSITIVE LOGITS
     never
    3.75
    never
    3.23
     Never
    3.19
    Never
    3.09
     NEVER
    2.66
     nunca
    2.57
    NEVER
    2.52
     nigdy
    2.42
     nooit
    2.36
     никогда
    2.27
    Activations Density 0.335%

    No Known Activations