© 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. 7692
    Prev
    Next
    INDEX
    Explanations

    information related to community forums and updates, particularly regarding bug tracking and other online discussions

    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
    +0.17
    0.5%
    924
    +0.10
    0.3%
    609
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.17
    0.04
    504
    +0.10
    0.04
    1465
    +0.08
    0.04
    Negative Logits
     hairc
    -1.14
     swarovski
    -1.12
     ecru
    -1.04
     cushi
    -1.04
     hoody
    -1.04
     gaily
    -1.02
     tupperware
    -0.99
     peppa
    -0.99
     oreo
    -0.95
     unspeak
    -0.95
    POSITIVE LOGITS
     solidar
    0.91
     utop
    0.83
     mena
    0.79
     ideolog
    0.79
     notor
    0.76
     meras
    0.76
     makro
    0.75
     geograf
    0.75
     kön
    0.74
     antik
    0.74
    Activations Density 0.123%

    No Known Activations