© 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. 2141
    Prev
    Next
    INDEX
    Explanations

    arguments and comparisons between different subjects

    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
    1150
    +0.20
    0.6%
    872
    +0.18
    0.5%
    604
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.20
    0.08
    963
    +0.18
    0.04
    1380
    +0.15
    0.02
    Negative Logits
     apprehen
    -0.75
    ihnachten
    -0.70
     redé
    -0.62
     rafra
    -0.61
     flé
    -0.60
     Voted
    -0.57
    ihnachts
    -0.54
     déchir
    -0.54
     McLaugh
    -0.53
     réglable
    -0.53
    POSITIVE LOGITS
    icrous
    0.59
     adulti
    0.58
     BnF
    0.56
     offrire
    0.56
    municipi
    0.54
     mezza
    0.52
    ziosi
    0.52
     stili
    0.51
     saper
    0.50
    cluye
    0.49
    Activations Density 0.747%

    No Known Activations