© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12339
    Prev
    Next
    INDEX
    Explanations

    personal and interpersonal details or stories related to individuals

    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
    1896
    +0.15
    0.5%
    776
    +0.14
    0.5%
    50
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.15
    0.04
    1984
    +0.14
    0.05
    382
    +0.13
    0.05
    Negative Logits
     delà
    -0.96
     tramonto
    -0.91
     medesimo
    -0.91
     seduta
    -0.90
     ruban
    -0.89
     BIBSYS
    -0.89
     stratigraph
    -0.88
     désert
    -0.88
     plancher
    -0.86
     coté
    -0.86
    POSITIVE LOGITS
     lot
    0.71
     handful
    0.69
     few
    0.68
     couple
    0.67
     multitude
    0.67
     plethora
    0.66
     variety
    0.60
     myriad
    0.60
     dozen
    0.58
     bunch
    0.58
    Activations Density 0.261%

    No Known Activations