© 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. 2062
    Prev
    Next
    INDEX
    Explanations

    instances where there is a temporal aspect or evolution

    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
    1678
    +0.10
    0.3%
    920
    +0.10
    0.3%
    1919
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.06
    862
    +0.10
    0.04
    1461
    +0.10
    0.05
    Negative Logits
     Mlle
    -1.17
     Ename
    -1.12
     matel
    -1.12
     lyon
    -1.10
     thut
    -1.09
     Quod
    -1.08
     Shakspeare
    -1.08
     ftu
    -1.06
     gabri
    -1.06
     napoli
    -1.06
    POSITIVE LOGITS
     been
    0.98
    been
    0.85
     BEEN
    0.82
    TintMode
    0.80
     succede
    0.73
    expandindo
    0.72
     become
    0.70
    ineno
    0.69
     gone
    0.68
     Walkover
    0.68
    Activations Density 0.222%

    No Known Activations