© 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. 14421
    Prev
    Next
    INDEX
    Explanations

    terms related to technological advancements and military information

    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
    1438
    +0.13
    0.4%
    1314
    +0.13
    0.4%
    1535
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.13
    0.07
    1314
    +0.13
    0.08
    1486
    +0.12
    0.05
    Negative Logits
     milf
    -0.96
     inev
    -0.89
     reluct
    -0.88
     indestru
    -0.86
     fuf
    -0.85
     depic
    -0.83
     parch
    -0.83
     kraken
    -0.83
     snoopy
    -0.82
     disagre
    -0.82
    POSITIVE LOGITS
     alike
    0.80
     moza
    0.59
     respectively
    0.59
     eki
    0.58
     eko
    0.58
     barna
    0.57
     koc
    0.56
     koz
    0.56
     kask
    0.55
     boks
    0.55
    Activations Density 0.500%

    No Known Activations