© 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. 3582
    Prev
    Next
    INDEX
    Explanations

    information related to news articles, URLs, and political issues

    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
    1343
    +0.26
    0.8%
    674
    +0.12
    0.4%
    1150
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.26
    0.04
    981
    +0.12
    0.03
    924
    +0.12
    0.03
    Negative Logits
     unspeak
    -1.62
     indestru
    -1.59
     apprehen
    -1.49
     swarovski
    -1.47
     impra
    -1.46
     gaily
    -1.45
     hairc
    -1.43
     disreg
    -1.42
     inconce
    -1.42
     fluo
    -1.42
    POSITIVE LOGITS
    <bos>
    1.00
    8
    0.70
    7
    0.69
    9
    0.67
    z
    0.66
    6
    0.65
    3
    0.64
    5
    0.64
    4
    0.64
    0
    0.63
    Activations Density 0.069%

    No Known Activations