Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8302
    Prev
    Next
    INDEX
    Explanations

    memories and experiences that had a significant impact on an individual or group

    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
    906
    +0.11
    0.3%
    1780
    +0.08
    0.2%
    1839
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1780
    +0.11
    0.03
    509
    +0.08
    0.04
    401
    +0.07
    0.02
    Negative Logits
     hcm
    -0.89
     jorge
    -0.84
     sergio
    -0.84
     guatemala
    -0.83
     santiago
    -0.83
     ricardo
    -0.82
     increa
    -0.79
     apprehen
    -0.79
     javier
    -0.79
     alberto
    -0.78
    POSITIVE LOGITS
     memory
    0.96
     memories
    0.94
    memory
    0.89
     remember
    0.87
    Memories
    0.78
    memories
    0.78
     remembers
    0.76
     recall
    0.76
     remembered
    0.76
     Memory
    0.75
    Activations Density 0.324%

    No Known Activations