© 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. 14660
    Prev
    Next
    INDEX
    Explanations

    references to significant historical or artistic events or projects

    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
    872
    +0.08
    0.2%
    2047
    +0.07
    0.2%
    776
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    65
    +0.08
    0.04
    2047
    +0.07
    0.03
    138
    +0.07
    0.04
    Negative Logits
     mef
    -0.79
     fischer
    -0.76
     kram
    -0.75
     alkoh
    -0.72
     daf
    -0.72
     franz
    -0.71
     gk
    -0.71
     fup
    -0.71
     hcm
    -0.71
     obé
    -0.70
    POSITIVE LOGITS
     landmark
    0.57
     paved
    0.56
     pivotal
    0.54
     groundbreaking
    0.54
     first
    0.54
     pioneering
    0.54
     pioneered
    0.53
     forever
    0.52
     milestone
    0.51
     revolution
    0.51
    Activations Density 0.360%

    No Known Activations