© 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. 3895
    Prev
    Next
    INDEX
    Explanations

    the names of different objects, concepts, or events in a given context, likely related to audience interest

    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
    227
    +0.11
    0.3%
    381
    +0.11
    0.3%
    382
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.11
    0.05
    62
    +0.11
    0.04
    16
    +0.10
    0.06
    Negative Logits
    ='".$
    -0.73
    AutoresizingMask
    -0.72
     dieses
    -0.69
    行
    -0.69
    REFERRED
    -0.68
    irical
    -0.67
    首
    -0.67
    но
    -0.67
    进
    -0.66
    全
    -0.66
    POSITIVE LOGITS
     accla
    2.44
     reluct
    2.38
     emphat
    2.34
     depic
    2.31
     embra
    2.27
     inev
    2.25
     desir
    2.24
     ftu
    2.23
     fath
    2.21
     fta
    2.21
    Activations Density 0.571%

    No Known Activations