© 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. 6783
    Prev
    Next
    INDEX
    Explanations

    details and reviews about software products

    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
    2019
    +0.23
    0.7%
    382
    +0.16
    0.5%
    1403
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.23
    0.08
    736
    +0.16
    0.06
    1959
    +0.16
    0.06
    Negative Logits
    enumi
    -0.62
     متعلقه
    -0.59
    roek
    -0.57
    enumii
    -0.57
     Wikimédia
    -0.56
    üy
    -0.54
    {}{}
    -0.53
     estekak
    -0.53
    存于互联网档案馆
    -0.53
    െയ
    -0.52
    POSITIVE LOGITS
     unlaw
    1.59
     impractica
    1.57
     encomp
    1.44
     reluct
    1.44
     guarante
    1.43
     volunte
    1.43
     affor
    1.42
     increa
    1.41
     impra
    1.36
     resear
    1.31
    Activations Density 0.532%

    No Known Activations