© 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. 13888
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and connectivity

    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
    1081
    +0.09
    0.2%
    197
    +0.08
    0.2%
    474
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1450
    +0.09
    0.02
    331
    +0.08
    0.03
    1809
    +0.08
    0.02
    Negative Logits
    Plusieurs
    -0.47
     pertanto
    -0.47
     perciò
    -0.45
     camaro
    -0.45
     camry
    -0.44
    Exemples
    -0.44
    asmussen
    -0.44
    oosevelt
    -0.44
     tuttavia
    -0.43
     chrysler
    -0.43
    POSITIVE LOGITS
     saka
    0.61
     	e
    0.51
     pama
    0.50
     tsi
    0.50
     nui
    0.47
     grati
    0.47
     vj
    0.46
     muna
    0.46
     kili
    0.45
     Journ
    0.45
    Activations Density 0.180%

    No Known Activations