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

    Neuronpedia

    Jacobian LensNEW
    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. 11481
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a process

    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
    184
    +0.20
    0.7%
    764
    +0.20
    0.6%
    876
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.20
    0.03
    736
    +0.20
    0.03
    184
    +0.18
    0.01
    Negative Logits
     alkoh
    -1.37
     meras
    -1.34
     akut
    -1.31
     kön
    -1.27
     Palestina
    -1.25
     keramik
    -1.21
     antik
    -1.21
     Meksiko
    -1.18
     monaster
    -1.17
     optik
    -1.17
    POSITIVE LOGITS
     unspeak
    2.02
     shenan
    1.93
     impra
    1.87
     impractica
    1.85
     tolerably
    1.84
     hairc
    1.82
     indestru
    1.81
     ecru
    1.80
     intersper
    1.79
     cushi
    1.77
    Activations Density 0.087%

    No Known Activations