© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4064
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Star Trek universe, especially focusing on the Klingons, the Federation, and specific characters and elements within the series

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    227
    +0.12
    0.4%
    86
    +0.11
    0.3%
    2015
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.07
    86
    +0.11
    0.02
    1987
    +0.10
    0.04
    Negative Logits
    enumii
    -0.53
    AnchorStyles
    -0.53
     utafitiHapana
    -0.49
    parseColor
    -0.48
    ChildScrollView
    -0.46
    MessageOf
    -0.45
    翁
    -0.45
    спонд
    -0.44
    fromLTRB
    -0.44
    IANGLES
    -0.44
    POSITIVE LOGITS
     emphat
    1.24
     tranf
    1.22
     excru
    1.16
     ftill
    1.16
     hairc
    1.16
     ftre
    1.16
     thut
    1.15
     ftu
    1.15
     paillettes
    1.11
     fign
    1.10
    Activations Density 0.610%

    No Known Activations