© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7318
    Prev
    Next
    INDEX
    Explanations

    references to historical events and locations

    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
    1133
    +0.12
    0.4%
    1150
    +0.10
    0.3%
    1482
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1133
    +0.12
    0.07
    1096
    +0.10
    0.05
    1482
    +0.10
    0.06
    Negative Logits
    المصادر
    -0.66
     كومونز
    -0.61
    UnitTesting
    -0.57
    Jako
    -0.56
    Glej
    -0.55
    المراجع
    -0.54
    Inne
    -0.54
    homem
    -0.52
    Referencie
    -0.51
    unidade
    -0.51
    POSITIVE LOGITS
     !...
    0.96
     ?...
    0.92
     fatis
    0.92
     increa
    0.91
     prodi
    0.89
     paff
    0.89
     fuf
    0.87
     fta
    0.87
     sii
    0.87
     purcha
    0.87
    Activations Density 0.096%

    No Known Activations