© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10799
    Prev
    Next
    INDEX
    Explanations

    instructions related to dealing with fraudulent accounts and creditors

    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
    1403
    +0.10
    0.3%
    776
    +0.10
    0.3%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    309
    +0.10
    0.04
    781
    +0.10
    0.03
    1165
    +0.09
    0.01
    Negative Logits
     newArr
    -1.10
     timeType
    -1.03
     companyId
    -1.02
     userType
    -1.01
     createdBy
    -1.00
     createDate
    -0.96
     newVal
    -0.93
     itemList
    -0.91
     userEmail
    -0.91
     resultList
    -0.90
    POSITIVE LOGITS
     date
    0.71
     details
    0.67
     description
    0.64
     location
    0.63
     dates
    0.61
     geogra
    0.59
     name
    0.59
    GEBURTS
    0.59
    примеча
    0.58
    date
    0.58
    Activations Density 0.393%

    No Known Activations