© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14618
    Prev
    Next
    INDEX
    Explanations

    phrases related to user interfaces and API development

    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
    1870
    +0.16
    0.6%
    316
    +0.14
    0.5%
    1742
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.16
    0.02
    404
    +0.14
    0.02
    1742
    +0.13
    0.02
    Negative Logits
     reluct
    -1.28
     viciss
    -1.26
     emphat
    -1.24
     accla
    -1.24
     indestru
    -1.21
     shenan
    -1.15
     Juf
    -1.14
     increa
    -1.14
     Khart
    -1.12
     excru
    -1.11
    POSITIVE LOGITS
     interface
    1.46
    interface
    1.37
    Interface
    1.31
     Interface
    1.27
     interfaces
    1.23
    INTERFACE
    1.08
    interfaces
    0.94
    Interfaces
    0.91
    接口
    0.90
     интерфей
    0.88
    Activations Density 0.087%

    No Known Activations