© 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. 13412
    Prev
    Next
    INDEX
    Explanations

    mentions of technical infrastructure and systems

    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
    1577
    +0.46
    1.8%
    1343
    +0.20
    0.8%
    1967
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.46
    0.22
    1531
    +0.20
    0.10
    184
    +0.14
    -0.00
    Negative Logits
    <bos>
    -1.30
    BeginInit
    -0.54
    ğlık
    -0.51
     AssemblyCulture
    -0.50
    లాలు
    -0.49
    Creed
    -0.44
     CreateTagHelper
    -0.43
     Walkover
    -0.43
    Hentet
    -0.43
    expandindo
    -0.42
    POSITIVE LOGITS
     zirc
    0.84
     friable
    0.81
     anhyd
    0.81
     chert
    0.79
     dolom
    0.78
     clayey
    0.78
     pollut
    0.75
     calcareous
    0.74
     embodi
    0.72
     bahia
    0.71
    Activations Density 7.374%

    No Known Activations