© 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. 7270
    Prev
    Next
    INDEX
    Explanations

    verbs related to processes or actions

    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
    411
    +0.17
    0.6%
    478
    +0.12
    0.5%
    25
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.17
    0.09
    1328
    +0.12
    0.07
    1415
    +0.11
    0.05
    Negative Logits
     matel
    -1.38
     cannes
    -1.31
     marseille
    -1.27
     bourgeo
    -1.27
     Rois
    -1.24
     fta
    -1.22
     Chinois
    -1.22
     Augu
    -1.22
     milano
    -1.21
     budapest
    -1.21
    POSITIVE LOGITS
     will
    1.01
    will
    0.90
     WILL
    0.86
     Will
    0.86
     be
    0.86
    Will
    0.82
    WILL
    0.82
     sẽ
    0.79
    ll
    0.77
     continue
    0.76
    Activations Density 0.252%

    No Known Activations