© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2251
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports, strategies, and evaluations

    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
    1166
    +0.11
    0.3%
    1531
    +0.10
    0.3%
    1092
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1166
    +0.11
    0.07
    1984
    +0.10
    0.06
    752
    +0.10
    0.04
    Negative Logits
    boon
    -0.54
     pamph
    -0.47
     vainly
    -0.47
    ragal
    -0.43
     kapak
    -0.42
     miscon
    -0.41
     columbia
    -0.40
    erjee
    -0.40
    kuva
    -0.40
     obstin
    -0.40
    POSITIVE LOGITS
     dirait
    0.61
     tourne
    0.59
     répon
    0.58
     tortas
    0.57
    Vaata
    0.57
     betweenstory
    0.57
     trouvera
    0.57
    Vegeu
    0.56
     ferait
    0.56
    dyž
    0.56
    Activations Density 0.526%

    No Known Activations