© 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. 12463
    Prev
    Next
    INDEX
    Explanations

    descriptions of real estate properties, specifically focusing on amenities and features

    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
    +0.28
    0.9%
    394
    +0.13
    0.4%
    678
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.28
    0.09
    1842
    +0.13
    0.07
    297
    +0.13
    0.07
    Negative Logits
    <bos>
    -1.04
     gyhoeddwyd
    -0.83
    pexpr
    -0.63
    UnitTesting
    -0.62
     "..\..\
    -0.62
     "..\..\..\
    -0.60
    ineno
    -0.60
     at
    -0.58
     by
    -0.58
     de
    -0.57
    POSITIVE LOGITS
     canel
    1.44
     affez
    1.41
     palab
    1.38
     napoli
    1.35
     alberto
    1.34
     dises
    1.32
     sappi
    1.32
     roberto
    1.30
     socie
    1.29
     igno
    1.28
    Activations Density 0.735%

    No Known Activations