© 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. 7549
    Prev
    Next
    INDEX
    Explanations

    phrases relating to sports news and player statistics

    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
    227
    +0.14
    0.4%
    1013
    +0.13
    0.4%
    2034
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.14
    0.09
    1013
    +0.13
    0.07
    483
    +0.12
    0.06
    Negative Logits
     swarovski
    -0.85
     interessa
    -0.81
     purtroppo
    -0.81
     specialmente
    -0.81
     sappi
    -0.80
     vuol
    -0.77
     rispond
    -0.76
     voleva
    -0.76
     faceva
    -0.75
     ognuno
    -0.74
    POSITIVE LOGITS
     herre
    0.60
     bourg
    0.59
     maneu
    0.58
     earlier
    0.57
     optik
    0.55
     last
    0.54
     akut
    0.52
     Kommune
    0.51
     previous
    0.51
     kontinu
    0.49
    Activations Density 0.577%

    No Known Activations