© 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. 13870
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific dates or events

    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
    1127
    +0.14
    0.6%
    878
    +0.14
    0.6%
    1065
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    689
    +0.14
    0.03
    981
    +0.14
    0.04
    678
    +0.14
    0.03
    Negative Logits
     own
    -0.52
     about
    -0.51
     of
    -0.51
     lavet
    -0.49
     أبريل
    -0.49
     Heritage
    -0.49
     الله
    -0.48
    什么
    -0.48
     like
    -0.48
    GARET
    -0.47
    POSITIVE LOGITS
     matel
    1.20
     squa
    1.12
     paillettes
    1.12
     immen
    1.12
     quoique
    1.10
     parteci
    1.08
     chande
    1.08
     casio
    1.06
     incess
    1.06
     autob
    1.05
    Activations Density 0.163%

    No Known Activations