© 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. 1049
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a period

    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
    1535
    +0.23
    0.7%
    2034
    +0.21
    0.7%
    382
    +0.19
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.23
    0.12
    1535
    +0.21
    0.09
    310
    +0.19
    0.06
    Negative Logits
     suspic
    -1.51
     emphat
    -1.48
     perfon
    -1.46
     pessi
    -1.43
     dises
    -1.42
     viciss
    -1.41
     abnorm
    -1.40
     sappi
    -1.38
     increa
    -1.38
     uncin
    -1.37
    POSITIVE LOGITS
    ↵↵
    0.97
     Therefore
    0.91
     And
    0.91
     So
    0.90
     There
    0.87
     For
    0.87
    <eos>
    0.84
     Still
    0.84
     The
    0.84
     In
    0.84
    Activations Density 0.494%

    No Known Activations