© 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. 2378
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to people's names, especially those associated with politics

    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
    537
    +0.14
    0.6%
    122
    +0.13
    0.6%
    228
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.14
    0.03
    981
    +0.13
    0.04
    1363
    +0.13
    0.03
    Negative Logits
    ahuila
    -0.52
    المراجع
    -0.48
    abstractmethod
    -0.46
    มาะ
    -0.45
    Referencer
    -0.44
    GOTREF
    -0.44
    richTextPanel
    -0.43
    typeorm
    -0.42
    粤
    -0.42
    rensen
    -0.42
    POSITIVE LOGITS
     Áng
    0.98
     Ing
    0.95
     sergio
    0.92
     ricardo
    0.91
     ING
    0.89
    Ing
    0.89
     jorge
    0.87
     Ging
    0.84
     LING
    0.84
     Zing
    0.81
    Activations Density 0.172%

    No Known Activations