© 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. 4042
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental policies and regulations

    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
    1499
    +0.19
    0.6%
    1403
    +0.12
    0.4%
    1120
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.19
    0.10
    939
    +0.12
    0.07
    1776
    +0.11
    0.03
    Negative Logits
     Mlle
    -1.24
     yoda
    -1.19
     hairc
    -1.18
     pixar
    -1.13
     milf
    -1.07
     ecru
    -1.05
     spiderman
    -1.04
     indescri
    -1.04
     inconce
    -1.02
     ninjago
    -1.01
    POSITIVE LOGITS
     teras
    1.02
     saar
    1.00
     kasa
    0.94
     kule
    0.89
     traktor
    0.85
     tyn
    0.85
     duk
    0.82
     marmor
    0.80
     kras
    0.80
     Ukraina
    0.78
    Activations Density 0.655%

    No Known Activations