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. 16-GEMMASCOPE-RES-16K
    6. 4766
    Prev
    Next
    INDEX
    Explanations

    terms related to the functionality and characteristics of mobile devices and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text occurring after specific conjunctions

    np_acts-logits-general · gemini-2.0-flash

    or followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.58
    RTEX
    -0.52
    hasErrors
    -0.51
    iedenis
    -0.47
    DockStyle
    -0.46
    נטרנט
    -0.44
    หวัด
    -0.43
     Disabilities
    -0.43
    attamento
    -0.43
    存于互联网档案馆
    -0.42
    POSITIVE LOGITS
    })*/
    0.72
     [],
    
    0.70
     inaczej
    0.69
    jooq
    0.65
     proprement
    0.63
    }*/
    
    0.63
    出版年
    0.61
    DrawerToggle
    0.61
     ?>/
    0.61
     quelquefois
    0.60
    Activations Density 0.354%

    No Known Activations