© 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 EvalsExportsinterp-engineNEWAPI 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. 4721
    Prev
    Next
    INDEX
    Explanations

    information related to rounds and time intervals

    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
    599
    +0.19
    0.6%
    453
    +0.15
    0.5%
    1336
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.19
    0.04
    1786
    +0.15
    0.01
    1336
    +0.14
    0.04
    Negative Logits
     unspeak
    -0.66
     pamph
    -0.60
     Wtf
    -0.59
     intersper
    -0.58
     gaily
    -0.58
     shenan
    -0.57
     deleteAll
    -0.55
     Lmao
    -0.55
     loggedIn
    -0.55
     beaute
    -0.54
    POSITIVE LOGITS
    DockStyle
    0.82
    SneakyThrows
    0.78
    onViewCreated
    0.76
     isoli
    0.75
    EndInit
    0.73
     maksi
    0.72
    ContentAsync
    0.71
     Referential
    0.69
     NDL
    0.67
    vible
    0.66
    Activations Density 0.194%

    No Known Activations