© 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. 12722
    Prev
    Next
    INDEX
    Explanations

    references to financial terms and technology concepts

    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
    0.6%
    453
    +0.10
    0.3%
    1965
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.20
    0.03
    453
    +0.10
    0.04
    1965
    +0.09
    0.03
    Negative Logits
     reluct
    -1.02
     encomp
    -0.97
     brilla
    -0.96
     McLaugh
    -0.94
     pamph
    -0.93
     Rine
    -0.92
     Vaugh
    -0.92
     disagre
    -0.91
     philanth
    -0.91
     volunte
    -0.88
    POSITIVE LOGITS
    mouseleave
    0.63
     taas
    0.56
     else
    0.52
    JsonFormat
    0.51
     아니라
    0.51
     juist
    0.51
    eleste
    0.50
     hingegen
    0.50
    Conversely
    0.50
    else
    0.49
    Activations Density 0.235%

    No Known Activations