© 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. 4302
    Prev
    Next
    INDEX
    Explanations

    commands and reports related to data processing and analysis

    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
    876
    +0.20
    0.6%
    1445
    +0.14
    0.4%
    2015
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.20
    -0.01
    1583
    +0.14
    0.03
    1445
    +0.12
    0.05
    Negative Logits
    <bos>
    -0.97
    Poder
    -0.82
     apart
    -0.80
    هذا
    -0.78
    الأ
    -0.77
    Esse
    -0.76
    على
    -0.76
    بعد
    -0.75
    इस
    -0.75
    的话
    -0.75
    POSITIVE LOGITS
     dispen
    2.86
     effe
    2.76
     wien
    2.70
     oner
    2.68
     embra
    2.62
     nutr
    2.61
     inder
    2.58
     michelin
    2.58
     stockholm
    2.58
     mef
    2.56
    Activations Density 0.378%

    No Known Activations