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. 18-GEMMASCOPE-RES-16K
    6. 14488
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collective or shared experiences

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

    Followed by "we," "our," or "other."

    np_acts-logits-general · gemini-2.0-flash

    "we" pronoun usage

    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
    hose
    -0.50
     herself
    -0.49
     astore
    -0.49
    Plans
    -0.48
    webElementXpaths
    -0.47
     Plans
    -0.45
    silia
    -0.44
    plans
    -0.44
    agit
    -0.42
    enné
    -0.42
    POSITIVE LOGITS
    出版年
    0.81
    ]")]
    0.71
     شاهد
    0.68
     tayo
    0.66
    клопе
    0.63
     invokingState
    0.61
     natin
    0.61
    drawiam
    0.61
    uxxxx
    0.60
    ########.
    0.60
    Activations Density 0.235%

    No Known Activations