© 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. 4262
    Prev
    Next
    INDEX
    Explanations

    descriptions of different parts of a building, including its size, facilities, and condition

    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
    1013
    +0.17
    0.5%
    738
    +0.15
    0.5%
    678
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.17
    0.05
    678
    +0.15
    0.04
    289
    +0.13
    0.02
    Negative Logits
    XmlEnum
    -0.66
    OfYear
    -0.60
     arată
    -0.57
    :"-
    -0.56
     bourg
    -0.53
     iliy
    -0.52
    ,$_
    -0.52
     downvoted
    -0.52
    )._
    -0.52
     subgoals
    -0.51
    POSITIVE LOGITS
     liberality
    0.73
     specchio
    0.66
    Sklici
    0.60
     Oggi
    0.60
     trouva
    0.59
     AVEC
    0.59
     stadio
    0.59
     bahay
    0.59
     dépens
    0.58
     amenities
    0.56
    Activations Density 0.314%

    No Known Activations