© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13324
    Prev
    Next
    INDEX
    Explanations

    words related to specific computer commands and instructions

    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
    871
    +0.12
    0.5%
    896
    +0.12
    0.5%
    381
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.12
    0.03
    871
    +0.12
    0.03
    370
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.08
    Eksteraj
    -0.68
    Referencer
    -0.67
    عرض
    -0.65
    GEBURTSDATUM
    -0.62
    Economía
    -0.60
    Fordítás
    -0.60
    Хоро
    -0.59
    película
    -0.58
     gekomen
    -0.58
    POSITIVE LOGITS
     wien
    1.36
     gend
    1.33
     lele
    1.29
     mef
    1.28
     dises
    1.27
     meis
    1.26
     bourgeo
    1.25
     gmbh
    1.25
     abnorm
    1.23
     grati
    1.23
    Activations Density 0.080%

    No Known Activations