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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14630
    Prev
    Next
    INDEX
    Explanations

    terms related to legal contracts and mechanisms for hiring staff

    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
    1870
    +0.12
    0.3%
    1150
    +0.11
    0.3%
    856
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1948
    +0.12
    0.05
    678
    +0.11
    0.05
    1870
    +0.08
    0.02
    Negative Logits
    DataPropertyName
    -0.54
     kasarigan
    -0.51
    SPJ
    -0.47
    částí
    -0.47
    úgó
    -0.46
    Geplaatst
    -0.46
    şağı
    -0.46
    ătate
    -0.46
     كومونز
    -0.46
    Dichloroethene
    -0.45
    POSITIVE LOGITS
     biais
    0.66
     Stretcher
    0.62
     newArr
    0.61
     resultList
    0.61
     riesce
    0.60
     intende
    0.58
     lumina
    0.57
     conosce
    0.57
     Ename
    0.57
     nmax
    0.56
    Activations Density 0.568%

    No Known Activations