© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 942
    Prev
    Next
    INDEX
    Explanations

    information related to personal memories 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
    776
    +0.09
    0.3%
    1081
    +0.07
    0.2%
    194
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.09
    0.06
    1650
    +0.07
    0.04
    167
    +0.07
    0.03
    Negative Logits
     beverly
    -0.83
     paula
    -0.81
     véhic
    -0.80
     frankfurt
    -0.79
     écout
    -0.78
     wikihow
    -0.78
     embodi
    -0.78
     levis
    -0.77
     obé
    -0.76
     increa
    -0.76
    POSITIVE LOGITS
     nostalgia
    1.06
     reminis
    1.02
     nostalgic
    1.01
     remembers
    0.91
     remembered
    0.91
     memories
    0.91
    stalgia
    0.91
     nostal
    0.89
     remembering
    0.87
     remember
    0.87
    Activations Density 1.227%

    No Known Activations