© 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. 14175
    Prev
    Next
    INDEX
    Explanations

    information related to video games and gaming culture, including discussions about gaming sales, gaming events, gaming technology, and gaming communities

    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
    690
    +0.10
    0.3%
    678
    +0.10
    0.3%
    304
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.10
    0.07
    2007
    +0.10
    0.04
    1702
    +0.09
    0.06
    Negative Logits
     fince
    -0.81
     ejus
    -0.74
     whofe
    -0.72
     caufe
    -0.68
     confider
    -0.66
     beft
    -0.66
     oxalate
    -0.64
    Vaata
    -0.63
     shewn
    -0.63
     gracilis
    -0.63
    POSITIVE LOGITS
     tricot
    0.86
     velour
    0.79
     legging
    0.76
     broderie
    0.76
     pyjama
    0.74
     cushi
    0.72
     bandeau
    0.71
     sherpa
    0.70
     hairc
    0.70
     lycra
    0.68
    Activations Density 1.185%

    No Known Activations