© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4038
    Prev
    Next
    INDEX
    Explanations

    words related to evaluating the consequences of actions or conditions, particularly in terms of their benefits or detriments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LabelTagHelper
    -0.61
    zonego
    -0.48
     escar
    -0.47
     arran
    -0.46
     betweenstory
    -0.46
    AndEndTag
    -0.46
    etra
    -0.45
     Falun
    -0.45
     Esperanto
    -0.45
    pau
    -0.45
    POSITIVE LOGITS
     beneficial
    0.73
    brainly
    0.72
     impact
    0.69
     effects
    0.66
     geweest
    0.66
    impact
    0.65
    ائص
    0.64
    effect
    0.63
     Effects
    0.62
     detriment
    0.61
    Activations Density 0.582%

    No Known Activations