© 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. 14297
    Prev
    Next
    INDEX
    Explanations

    adjectives describing difficulty or ease

    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
    1839
    +0.11
    0.3%
    1609
    +0.09
    0.3%
    689
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1839
    +0.11
    0.05
    1176
    +0.09
    0.04
    1609
    +0.08
    0.05
    Negative Logits
     alkoh
    -1.07
     meras
    -1.05
     valla
    -1.05
     solidar
    -1.03
     minimalis
    -1.03
     Strukt
    -1.01
     Singapur
    -0.99
     sement
    -0.99
     kram
    -0.99
     lemp
    -0.99
    POSITIVE LOGITS
     to
    0.81
     for
    0.60
     jemanden
    0.58
     uwag
    0.58
     człowie
    0.57
     geweest
    0.55
     uitgenodigd
    0.52
     Schluß
    0.52
     wcześ
    0.52
     rocz
    0.51
    Activations Density 0.157%

    No Known Activations