© 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. 13906
    Prev
    Next
    INDEX
    Explanations

    phrases related to learning lessons and experiences

    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
    30
    +0.09
    0.3%
    892
    +0.09
    0.2%
    401
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.09
    0.03
    30
    +0.09
    0.03
    1030
    +0.08
    0.02
    Negative Logits
     casio
    -0.51
     unwarran
    -0.49
     Intere
    -0.46
     Etat
    -0.46
     afp
    -0.45
     cytoplas
    -0.45
     explication
    -0.45
     Réalisation
    -0.44
     logitech
    -0.44
     apprehen
    -0.43
    POSITIVE LOGITS
     lessons
    0.92
     learned
    0.91
     learn
    0.91
     lesson
    0.87
     learnt
    0.84
     learning
    0.83
     Learned
    0.82
     LEARN
    0.82
    learn
    0.81
     learns
    0.81
    Activations Density 0.170%

    No Known Activations