© 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. 13706
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or controversial topics

    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
    1589
    +0.08
    0.2%
    62
    +0.08
    0.2%
    1379
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.08
    0.04
    1379
    +0.08
    0.03
    382
    +0.07
    0.04
    Negative Logits
    awtextra
    -0.64
    MessageOf
    -0.61
     bonté
    -0.59
    Komple
    -0.59
     dignité
    -0.58
     notori
    -0.57
    Preparación
    -0.57
     intit
    -0.57
     notor
    -0.57
     Normdatei
    -0.57
    POSITIVE LOGITS
     still
    1.01
     STILL
    1.00
     nevertheless
    0.92
    still
    0.92
     nonetheless
    0.87
     stills
    0.82
     tolerably
    0.82
     ftill
    0.81
     intersper
    0.81
     Still
    0.80
    Activations Density 0.293%

    No Known Activations