© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3345
    Prev
    Next
    INDEX
    Explanations

    questions and statements regarding personal identity and existential themes

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

    Token before coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    referencing types, sequences, or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -1.09
    fromnode
    -0.95
    
    -0.93
    MessageTagHelper
    -0.93
     ſche
    -0.92
     fevere
    -0.92
     EconPapers
    -0.90
    ……"
    -0.87
     myſelf
    -0.86
     ſtate
    -0.86
    POSITIVE LOGITS
    <bos>
    0.94
     and
    0.76
     but
    0.72
     which
    0.61
     or
    0.59
     as
    0.58
     even
    0.56
     that
    0.56
     whose
    0.55
    and
    0.54
    Activations Density 0.122%

    No Known Activations