Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 8233
    Prev
    Next
    INDEX
    Explanations

    terms related to permanence and irreversible conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ῖν
    -0.78
     nakalista
    -0.77
    ]$}
    -0.75
    énario
    -0.74
     createSlice
    -0.71
    BeginContext
    -0.70
     INTERESAR
    -0.68
     يتيمه
    -0.65
     }{@
    -0.65
    AccessorTable
    -0.64
    POSITIVE LOGITS
     permanent
    1.48
     forever
    1.46
     permanently
    1.37
     Permanent
    1.35
    permanent
    1.32
     FOREVER
    1.31
     Forever
    1.31
    forever
    1.28
     Perman
    1.24
     PERMAN
    1.23
    Activations Density 0.152%

    No Known Activations