© 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. 10882
    Prev
    Next
    INDEX
    Explanations

    examples or references to contrasting aspects or situations

    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
    1842
    +0.10
    0.3%
    198
    +0.10
    0.3%
    152
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.10
    0.01
    152
    +0.10
    0.04
    1533
    +0.09
    0.01
    Negative Logits
     accla
    -1.23
     pessi
    -1.20
     wherea
    -1.19
     emphat
    -1.17
     inder
    -1.17
     strick
    -1.17
     reluct
    -1.15
     uniqu
    -1.13
     intermitt
    -1.13
     coö
    -1.12
    POSITIVE LOGITS
     including
    0.82
    including
    0.80
    such
    0.68
    比如
    0.68
    包括
    0.66
    גון
    0.63
     zvuky
    0.63
     Including
    0.62
     such
    0.62
    例えば
    0.62
    Activations Density 0.459%

    No Known Activations