© 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. 16176
    Prev
    Next
    INDEX
    Explanations

    dates expressed in text

    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
    2034
    +0.15
    0.5%
    1150
    +0.13
    0.4%
    856
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1376
    +0.15
    0.05
    1372
    +0.13
    0.04
    1781
    +0.11
    0.04
    Negative Logits
     Ottobre
    -0.78
     peppa
    -0.77
     Luglio
    -0.76
     LIRE
    -0.74
     swarovski
    -0.73
     sappi
    -0.73
     dicono
    -0.72
     dichi
    -0.71
     tupperware
    -0.70
     nutella
    -0.68
    POSITIVE LOGITS
    OURCES
    0.75
     Republics
    0.64
    oforms
    0.61
     alip
    0.59
    ValueStyle
    0.58
    ANNEL
    0.56
    Newswire
    0.56
    IPMENT
    0.56
    URNS
    0.56
    FACES
    0.56
    Activations Density 0.152%

    No Known Activations