© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7681
    Prev
    Next
    INDEX
    Explanations

    words related to political events and legislation

    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
    332
    +0.12
    0.3%
    604
    +0.08
    0.2%
    612
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1600
    +0.12
    0.04
    1114
    +0.08
    0.03
    332
    +0.08
    0.03
    Negative Logits
     maneu
    -1.41
     disreg
    -1.34
     shenan
    -1.34
     impra
    -1.24
     resear
    -1.23
     stickied
    -1.23
     snoopy
    -1.22
     reluct
    -1.19
     practition
    -1.17
     horrend
    -1.17
    POSITIVE LOGITS
     “
    0.71
     "
    0.67
    “
    0.67
     «
    0.67
    Handlung
    0.61
    ModelAttribute
    0.61
     jPanel
    0.58
     „
    0.55
    「
    0.55
    RequestMapping
    0.55
    Activations Density 0.368%

    No Known Activations