Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 4326
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal preferences and opinions

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

    Following "it," "us," or a similar pronoun

    np_acts-logits-general · gemini-2.0-flash

    love and like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.80
     nakalista
    -0.76
    EndContext
    -0.68
    LEEP
    -0.55
     энциклопедия
    -0.55
    )}_
    -0.53
    PyErr
    -0.53
    transQ
    -0.52
    tableFuture
    -0.52
    insics
    -0.52
    POSITIVE LOGITS
     enough
    1.06
     dearly
    0.97
     more
    0.96
     mucho
    0.93
     much
    0.91
     autant
    0.88
     lắm
    0.83
     immensely
    0.83
     suffisamment
    0.83
     enemmän
    0.78
    Activations Density 0.183%

    No Known Activations