© 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. 13342
    Prev
    Next
    INDEX
    Explanations

    names of organizations and entities

    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
    +0.09
    0.3%
    453
    +0.07
    0.2%
    1870
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1494
    +0.09
    0.06
    648
    +0.07
    0.04
    1720
    +0.07
    0.03
    Negative Logits
     époux
    -0.83
     delà
    -0.82
     créateur
    -0.80
     broderie
    -0.77
     vainqueur
    -0.74
     vôtre
    -0.74
     ecru
    -0.73
     lapin
    -0.72
     malheureux
    -0.72
     coté
    -0.72
    POSITIVE LOGITS
    Herzlich
    0.70
    <bos>
    0.63
     Junio
    0.62
     Tanja
    0.61
     Elke
    0.61
    Gobierno
    0.61
     ideolog
    0.60
     Siglo
    0.60
     Dage
    0.59
     Sú
    0.59
    Activations Density 0.429%

    No Known Activations