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. 15-GEMMASCOPE-RES-16K
    6. 2090
    Prev
    Next
    INDEX
    Explanations

    legal actions or proceedings involving judicial reviews or petitions

    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
    tagHelperRunner
    -0.62
     noten
    -0.57
    GraphicsUnit
    -0.56
    OCCURRED
    -0.54
     GetEnumerator
    -0.53
     blanches
    -0.51
    󠁣
    -0.50
     tamu
    -0.49
    ̍
    -0.49
     &___
    -0.48
    POSITIVE LOGITS
    InitVars
    0.61
    訟
    0.60
     court
    0.56
    讼
    0.54
     litigation
    0.54
     libel
    0.54
    oredCriteria
    0.54
     case
    0.53
     litig
    0.52
     trial
    0.52
    Activations Density 2.298%

    No Known Activations