© 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. 15-GEMMASCOPE-RES-16K
    6. 8348
    Prev
    Next
    INDEX
    Explanations

    concepts related to permanence and irreversible actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ApiModel
    -0.60
    */),
    -0.56
     }}"></
    -0.54
     Biôgrafia
    -0.52
     Roskov
    -0.51
    Билгалдахарш
    -0.51
    matchCondition
    -0.50
    endphp
    -0.49
     مشين
    -0.47
    AndEndTag
    -0.47
    POSITIVE LOGITS
     permanently
    1.45
     permanent
    1.34
    permanent
    1.21
     Permanent
    1.17
    Permanent
    1.14
     définitivement
    1.13
     PERMAN
    1.10
     forever
    1.09
     Perman
    1.08
    perman
    1.04
    Activations Density 0.257%

    No Known Activations