© 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. 2349
    Prev
    Next
    INDEX
    Explanations

    text related to technical explanations or concepts with a focus on detail and precise terms

    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
    872
    +0.11
    0.3%
    1793
    +0.09
    0.3%
    547
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1793
    +0.11
    0.06
    1601
    +0.09
    0.05
    100
    +0.07
    0.05
    Negative Logits
     „,
    -1.13
     peculi
    -1.13
     embra
    -1.09
     fte
    -1.08
     tew
    -1.05
     blos
    -1.05
     lein
    -1.05
     autob
    -1.05
     fta
    -1.04
     accla
    -1.03
    POSITIVE LOGITS
     that
    1.09
    that
    1.01
     rằng
    0.97
     bahwa
    0.84
     dass
    0.83
    That
    0.81
     That
    0.75
     THAT
    0.72
     что
    0.69
     که
    0.68
    Activations Density 0.333%

    No Known Activations