© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    information related to business acquisitions and historical events

    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
    1042
    +0.10
    0.3%
    994
    +0.08
    0.2%
    314
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.10
    0.03
    623
    +0.08
    0.03
    446
    +0.08
    0.03
    Negative Logits
     tanong
    -0.68
    idać
    -0.65
    ypeł
    -0.58
     smtplib
    -0.57
     NUKAT
    -0.57
    lepiej
    -0.57
     buhay
    -0.57
     bawat
    -0.56
     loob
    -0.54
    Trimethyl
    -0.54
    POSITIVE LOGITS
     longest
    0.72
     largest
    0.71
     shortest
    0.67
     oldest
    0.66
     lowest
    0.66
     smallest
    0.65
     widest
    0.64
     heaviest
    0.63
     slowest
    0.63
     foremost
    0.63
    Activations Density 0.136%

    No Known Activations