© 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. 14-GEMMASCOPE-RES-16K
    6. 5737
    Prev
    Next
    INDEX
    Explanations

    terms related to software and its definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tare
    -0.71
     Hưng
    -0.70
     ActionResult
    -0.67
     Shanks
    -0.65
    adpleegd
    -0.64
     Sentry
    -0.64
    unci
    -0.64
    opardy
    -0.64
     Rebirth
    -0.63
    Isolate
    -0.63
    POSITIVE LOGITS
     software
    1.35
     Software
    1.25
    oftware
    1.13
    software
    1.11
    Software
    1.11
     softwares
    1.09
    SOFTWARE
    1.06
     SOFTWARE
    1.02
     软件
    0.97
    软件
    0.95
    Activations Density 0.044%

    No Known Activations