© 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. 13701
    Prev
    Next
    INDEX
    Explanations

    information related to funding rounds, fundraising, and mergers in the context of companies and organizations

    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
    453
    +0.13
    0.4%
    674
    +0.13
    0.4%
    964
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.13
    0.05
    1362
    +0.13
    0.02
    934
    +0.13
    0.02
    Negative Logits
     indestru
    -1.16
     !...
    -1.12
     hairc
    -1.11
     maneu
    -1.07
     scrat
    -1.06
     fign
    -1.05
     increa
    -1.05
     ftu
    -1.04
     disreg
    -1.04
     suscep
    -1.03
    POSITIVE LOGITS
    <bos>
    0.76
    <u>
    0.55
     Pristupljeno
    0.52
     reportedly
    0.52
     
    0.52
     برابوك
    0.52
    ‍
    0.52
     recently
    0.51
    Биография
    0.49
     snippetHide
    0.49
    Activations Density 0.426%

    No Known Activations