© 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. 943
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms used in relations and equivalence

    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
    1343
    +0.21
    0.6%
    453
    +0.13
    0.4%
    297
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.21
    0.04
    1343
    +0.13
    0.03
    981
    +0.12
    0.03
    Negative Logits
    <bos>
    -0.98
     święta
    -0.66
    यास
    -0.59
     wanderer
    -0.57
     Савезне
    -0.57
     countryman
    -0.56
     courtier
    -0.56
     schoolboy
    -0.55
     schoolmaster
    -0.53
     vermek
    -0.53
    POSITIVE LOGITS
     brille
    1.12
     contribue
    1.12
     espres
    1.09
     sappi
    1.07
     trovo
    1.05
     remonte
    1.04
     abbra
    1.03
     affez
    1.02
     affatto
    1.02
     exé
    1.02
    Activations Density 0.107%

    No Known Activations