© 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. 2518
    Prev
    Next
    INDEX
    Explanations

    phrases related to fitness training and workout routines

    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
    876
    +0.12
    0.3%
    1823
    +0.10
    0.3%
    74
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1823
    +0.12
    0.04
    163
    +0.10
    0.02
    1877
    +0.09
    0.04
    Negative Logits
     ecclesias
    -0.65
     alkoh
    -0.64
     antik
    -0.63
     Sigism
    -0.63
     kompati
    -0.62
     Sitten
    -0.62
     Wikisource
    -0.62
     beker
    -0.60
     Encyclopædia
    -0.60
     plebis
    -0.59
    POSITIVE LOGITS
     hairc
    1.06
     ecru
    0.98
     tupperware
    0.94
     velour
    0.90
     lycra
    0.86
     swarovski
    0.83
     amigurumi
    0.81
     broderie
    0.79
     shenan
    0.79
     cushi
    0.77
    Activations Density 0.660%

    No Known Activations