© 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. 7616
    Prev
    Next
    INDEX
    Explanations

    sentences related to rules and instructions with emphasis on specific positive/negative comparisons and outlines for improvement

    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
    394
    +0.12
    0.3%
    270
    +0.09
    0.3%
    1648
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.12
    0.05
    1648
    +0.09
    0.02
    1328
    +0.09
    0.04
    Negative Logits
     lele
    -1.23
     kasa
    -1.08
     saha
    -1.02
     karton
    -1.02
     kac
    -1.01
     makro
    -0.98
     kase
    -0.96
     bera
    -0.96
     seksi
    -0.94
     teras
    -0.94
    POSITIVE LOGITS
     ecru
    0.66
    ğinde
    0.63
     chcą
    0.63
    ğine
    0.62
    Może
    0.60
    ENODEV
    0.60
    áklad
    0.60
     dintr
    0.59
    πάρχ
    0.58
     poteva
    0.57
    Activations Density 0.529%

    No Known Activations