© 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. 13763
    Prev
    Next
    INDEX
    Explanations

    explanations or reasoning in a text

    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
    1150
    +0.09
    0.3%
    946
    +0.09
    0.3%
    1438
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.09
    0.05
    1533
    +0.09
    0.02
    1056
    +0.08
    0.05
    Negative Logits
    Lma
    -1.24
    Ikr
    -1.23
    FTFY
    -1.21
    Lmfao
    -1.20
    
    -1.08
     uefa
    -1.06
    Noice
    -1.03
     sappi
    -0.99
    <?
    -0.97
    Yess
    -0.93
    POSITIVE LOGITS
     they
    0.71
     that
    0.67
     he
    0.62
     it
    0.62
     she
    0.60
     if
    0.60
     there
    0.59
     we
    0.57
     you
    0.57
     told
    0.57
    Activations Density 0.309%

    No Known Activations