© 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. 13743
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in the context of various industries like games, computing, and entertainment

    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
    1343
    +0.31
    1.1%
    1741
    +0.22
    0.8%
    382
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.31
    0.06
    382
    +0.22
    0.05
    1343
    +0.18
    0.05
    Negative Logits
     sprend
    -0.64
     dager
    -0.62
     asado
    -0.61
    FORMANCE
    -0.60
    PONENTS
    -0.59
     špat
    -0.59
     különböz
    -0.58
     poważ
    -0.58
     måneder
    -0.58
     forsø
    -0.58
    POSITIVE LOGITS
     confé
    0.89
     supplé
    0.84
     vôtre
    0.81
     vété
    0.80
     nôtre
    0.80
     Cfr
    0.80
     Gemeinsame
    0.77
     éclairage
    0.76
     réfé
    0.76
     Anm
    0.76
    Activations Density 0.201%

    No Known Activations