© 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. 6501
    Prev
    Next
    INDEX
    Explanations

    legal or political terms and phrases

    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
    605
    +0.13
    0.4%
    924
    +0.13
    0.4%
    678
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.13
    0.03
    605
    +0.13
    0.01
    1740
    +0.11
    0.01
    Negative Logits
    ↵↵
    -0.71
     on
    -0.68
     or
    -0.66
     de
    -0.65
     and
    -0.65
     en
    -0.65
    ,
    -0.65
     as
    -0.65
     $\
    -0.64
    ↵
    -0.63
    POSITIVE LOGITS
     fatis
    1.51
    fordable
    1.48
     ftu
    1.45
     viciss
    1.41
     sovere
    1.38
     jaya
    1.37
     alberto
    1.36
     juft
    1.35
     bandung
    1.34
     frankfurt
    1.34
    Activations Density 0.085%

    No Known Activations