© 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. 14667
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the addition of information or the expressing of an opinion

    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
    32
    +0.13
    0.4%
    568
    +0.12
    0.4%
    1265
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.13
    0.04
    568
    +0.12
    0.04
    131
    +0.10
    0.03
    Negative Logits
     thermomix
    -0.93
     Confe
    -0.79
     Simult
    -0.78
     vito
    -0.75
     pican
    -0.74
     canel
    -0.73
     churrasco
    -0.73
     socie
    -0.72
     ecclesias
    -0.71
     Consig
    -0.69
    POSITIVE LOGITS
     added
    0.95
     adding
    0.93
    added
    0.89
     add
    0.89
     ADDED
    0.85
     adds
    0.84
     Added
    0.82
    adding
    0.81
     addition
    0.79
    Added
    0.78
    Activations Density 0.058%

    No Known Activations