© 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. 12529
    Prev
    Next
    INDEX
    Explanations

    phrases related to tasks or instructions

    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
    1387
    +0.14
    0.5%
    47
    +0.14
    0.5%
    1124
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.14
    0.06
    1387
    +0.14
    0.06
    1124
    +0.10
    0.05
    Negative Logits
     Phú
    -0.46
    ㎜
    -0.46
    PathParam
    -0.45
    MILLISECONDS
    -0.44
    BindingResult
    -0.44
     which
    -0.44
     Instrum
    -0.42
     erhoben
    -0.42
    9
    -0.42
    ulipas
    -0.41
    POSITIVE LOGITS
     effe
    1.14
     embodi
    1.07
     perfon
    1.07
     ftu
    1.05
     unce
    1.05
     tranf
    1.04
     nece
    1.01
     reft
    1.01
     unden
    0.99
     erec
    0.99
    Activations Density 0.128%

    No Known Activations