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. 3-GEMMASCOPE-RES-16K
    6. 9936
    Prev
    Next
    INDEX
    Explanations

    references to valves and their related components in mechanical or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.91
     Blount
    -0.88
     Zagreb
    -0.88
    — 
    -0.86
    ]='\
    -0.84
    ientôt
    -0.84
    RuleContext
    -0.84
    脚注の使い方
    -0.83
     Mota
    -0.83
    逅
    -0.81
    POSITIVE LOGITS
     Williams
    1.10
     Stephen
    0.99
    Williams
    0.92
    zz
    0.91
    Stephen
    0.85
     Russell
    0.79
     SC
    0.76
    Russell
    0.70
     valves
    0.70
     valve
    0.70
    Activations Density 0.063%

    No Known Activations