© 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. 13345
    Prev
    Next
    INDEX
    Explanations

    mentions of alcohol consumption and behavioral changes related to drinking habits

    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
    1253
    +0.14
    0.4%
    198
    +0.13
    0.4%
    1445
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.14
    0.04
    1025
    +0.13
    0.06
    1253
    +0.11
    0.03
    Negative Logits
     encomp
    -1.22
     swarovski
    -1.15
     felicity
    -1.11
     embodi
    -1.11
     indestru
    -1.09
     Shakspeare
    -1.07
     brilli
    -1.04
    <^
    -1.04
     intersper
    -1.01
     reft
    -0.99
    POSITIVE LOGITS
     Pediat
    0.62
     gubern
    0.61
     prostitu
    0.61
     revisor
    0.59
     nationwide
    0.59
     lapto
    0.58
     churras
    0.58
     Estat
    0.58
     gymnas
    0.55
     luka
    0.55
    Activations Density 0.563%

    No Known Activations