© 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. 12814
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular biology, such as protein names, amino acids, genes, and specific biological processes

    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
    +0.27
    0.9%
    1150
    +0.13
    0.5%
    876
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.27
    0.04
    736
    +0.13
    0.05
    950
    +0.12
    0.05
    Negative Logits
    该如何
    -0.54
    nowu
    -0.54
     OnTrigger
    -0.53
    是这样的
    -0.53
    就行
    -0.52
    崩壊
    -0.52
    是为了
    -0.52
    结尾
    -0.51
    上涨
    -0.51
    一段时间
    -0.51
    POSITIVE LOGITS
     dises
    1.31
     effe
    1.17
     inev
    1.14
     mef
    1.13
     nece
    1.11
     ftu
    1.09
     kram
    1.09
     sovere
    1.08
     fta
    1.06
     pessi
    1.05
    Activations Density 0.148%

    No Known Activations