© 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. 4312
    Prev
    Next
    INDEX
    Explanations

    instances where the word 'only' appears with a high activation value

    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
    1820
    +0.07
    0.2%
    254
    +0.07
    0.2%
    946
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1820
    +0.07
    0.03
    1100
    +0.07
    0.03
    254
    +0.07
    0.03
    Negative Logits
     kosme
    -1.13
     alkoh
    -1.10
     keramik
    -1.06
     minimalis
    -1.06
     solidar
    -1.05
     kompati
    -1.03
     antik
    -1.00
     akus
    -0.99
     kriminal
    -0.98
     mikrofon
    -0.98
    POSITIVE LOGITS
     does
    0.94
     did
    0.88
     do
    0.79
     Does
    0.79
    does
    0.73
     vainly
    0.72
     are
    0.65
     impelled
    0.65
    Może
    0.65
    Does
    0.65
    Activations Density 0.169%

    No Known Activations